tag:blogger.com,1999:blog-18720268537457007702024-03-13T01:28:43.294-07:00All About AnalyticsCustomer Analytics, Supply Chain Analytics, Next Best Offer, Next Best Action, Consumer Behavioral Prediction, Social Analytics, Social Media Analytics, Location based Analytics, SoLoMo Analytics, Predictive Modelling, PMML, Statistical Models, Statistical Modelling, Revolutionary R, SAS, SPSS, Demand Forecasting, Product Affinity Analysis, Offer Response Model, Customer Intelligence Modeling, Machine LearningUnknownnoreply@blogger.comBlogger38125tag:blogger.com,1999:blog-1872026853745700770.post-56982084604655729572014-03-22T07:20:00.002-07:002014-03-22T07:20:46.550-07:00How to Identify Right Shopper for Promotions / How to Categorize Shoppers based on Loyalty<h2>
<span style="color: red; font-family: Trebuchet MS, sans-serif;">Identify Profitable Shoppers using Statistical Modeling</span></h2>
<span style="font-family: Trebuchet MS, sans-serif;"><br /></span>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg4ULnetzLWY3jXUUQc4uuKV1fggGx196NgVwBr1lXNpHINK5hz_uIDWDq7HCA3f_Uly5wW9d0vkhlMucm8UpZySmDcVL7GhQearFa413l5SjEa5jETEq101-yf-x3tDUeEeW437lOxt7w/s1600/girl-at-shopping-hd-wallpaper-57291.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg4ULnetzLWY3jXUUQc4uuKV1fggGx196NgVwBr1lXNpHINK5hz_uIDWDq7HCA3f_Uly5wW9d0vkhlMucm8UpZySmDcVL7GhQearFa413l5SjEa5jETEq101-yf-x3tDUeEeW437lOxt7w/s1600/girl-at-shopping-hd-wallpaper-57291.jpg" height="200" width="320" /></a><span style="font-family: Trebuchet MS, sans-serif;">Not all shoppers are profitable - the statement sounds bit confusing. But a careful analysis shows that there are some who buy only during Mark Downs, select low margin products in discounts etc. In the previous posts <span style="background-color: white;"><a href="http://analyticsdud.blogspot.in/2012/12/what-are-steps-in-nbo-next-best-offer.html" target="_blank">What are the steps in NBO (Next Best Offer) to give Personalized Promotion</a> and <a href="http://analyticsdud.blogspot.in/2013/03/what-are-key-channels-to-be-considered.html" target="_blank">Find Right Channel</a> we get an idea of how to select a right product for promotion and what would be the appropriate time for sending the promotion/offer</span></span><br />
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;"><br /></span></span>
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;">Well before attaching an offer to the customer, one needs to select if the customer is profitable for the loyalty program</span></span><br />
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;"><br /></span></span>
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;">There are many methods to check if the customer is profitable. This is is based on the past transaction history and applying methods / models on them</span></span><br />
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;"><br /></span></span>
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;">CLV and NPV are some techniques to use in the current scenario. <a href="http://analyticsdud.blogspot.in/2013/02/segmentation-standards-framework.html" target="_blank">Segmentation </a>of customers based on the above would provide a good insights</span></span><br />
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;"><br /></span></span>
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;">This is a challenge for many US Retailers whose customers enroll in multiple loyalty programs (Average US household enrolls to 23 loyalty programs) and hip hop to other retailer based on Sale/Discount. <a href="http://analyticsdud.blogspot.in/2013/04/customer-analytics-relative-price-as.html" target="_blank">Price plays an important role</a> in this</span></span><br />
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;"><br /></span></span>
<span style="background-color: white;"><span style="font-family: Trebuchet MS, sans-serif;">According to a study by </span></span><a class="g-profile" href="https://plus.google.com/106839023015603491740" style="background-color: white; font-family: 'Trebuchet MS', sans-serif;" target="_blank">+McKinsey on Marketing & Sales</a><span style="background-color: white; font-family: 'Trebuchet MS', sans-serif;"> targeting High Value customers is one of the way to improve the Basket Size (both items and Value). One of every retailer's goal should be to Increase the Basket Size by appropriate promotions</span>Unknownnoreply@blogger.com2tag:blogger.com,1999:blog-1872026853745700770.post-72687944294195713692014-01-25T23:03:00.001-08:002014-01-25T23:03:20.046-08:00Sports Analytics - Use of Big Data Analytics in Sports<h2>
<span style="color: red;">Sports Analytics - The next use case for Big Data Analytics</span></h2>
Sportsmen and Sportswoman are not data mines, their actions are supposed to be based on fitness, confidence and skills and are supposed to be subjective.<br />
<br />
Not anymore. Though their height, weight and the fitness were measured earlier .. the new Big Data analytics stores every<br />
<h3>
<span style="color: blue;">SaberMetrics - the Bellwether </span></h3>
<br />
Billy Beane - Oakland Athletics general manager and baseball guru - used metrics to choose baseball players. He used an evidence-based analytics approach called sabermetrics to pick certain “diamond in the rough” players for his team. These players were evaluated by situational and predictive metrics, rather than common stats like home runs and batting average, representing a significant shift in the way the baseball industry established their teams.
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjm17o9KiJkgPkvKUCvsTKBb_Yx8PsFHw-pIGXLL_gSprpAF0LyALB1cdRMV0URuQub70Ok8uPb9pWNf8avmDURhyDsnnMF0Ij3_2loX4SlRZDnbDRGBriqd4FCu7a0ZpAMmnJmm4B6vx8/s1600/Sania+Mirza.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjm17o9KiJkgPkvKUCvsTKBb_Yx8PsFHw-pIGXLL_gSprpAF0LyALB1cdRMV0URuQub70Ok8uPb9pWNf8avmDURhyDsnnMF0Ij3_2loX4SlRZDnbDRGBriqd4FCu7a0ZpAMmnJmm4B6vx8/s1600/Sania+Mirza.jpg" height="194" width="320" /></a><br />
THere are many sports and games wHere analytiCs an Help, for example, Tennis<br />
<br />
Understanding tHe player's potential would Help the manager fine tune the player<br />
Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-50915303450955307212013-10-14T01:02:00.003-07:002014-03-16T09:08:00.634-07:00Advanced Analytics in Learning / Education / Writing / Research<om name="Om Ganeshaya Namaha">
<om name="Om Satguru Seshadri Swamigal Thiruvadike">
<om name="Om Varahi Namaha">
<om name="Om Saravana Bhava">
<om name="Om Sai Ram">
<om name="Om Namah Shivaya">
<om name="Om Shakthi">
<om name="Om Namo Narayana">
<om name="Hari Om!">
<om name="Jai Shri Ram">
<br /><b><span style="color: #20124d; font-size: large;">
How will Analytics help Education in Schools and Colleges
</span></b></om></om></om></om></om></om></om></om></om></om><br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiAd2oBsfHgyVQA_lqq3FhXXgp3Q-RkyzYvTULVIjkYMsRKJ0_GP7TCxbzKp7WxyiTw2jD02qPVL3M_0q8zVOlGeqzp62DgILQmfnayrrKab6feldQ-CTPViC4a3t4jzvB3vZ_TSqPEtCA/s1600/Declara.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiAd2oBsfHgyVQA_lqq3FhXXgp3Q-RkyzYvTULVIjkYMsRKJ0_GP7TCxbzKp7WxyiTw2jD02qPVL3M_0q8zVOlGeqzp62DgILQmfnayrrKab6feldQ-CTPViC4a3t4jzvB3vZ_TSqPEtCA/s320/Declara.png" height="288" width="320" /></a><om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram"><br /></om></om></om></om></om></om></om></om></om></om>
<om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram">Educational institutions (Schools and Colleges) are a good place for Analytics - for they have data for analyzing. However, very few colleges / schools use the data mining to get the insights on their students. </om></om></om></om></om></om></om></om></om></om><br />
<om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram"><br /></om></om></om></om></om></om></om></om></om></om>
<br />
<a href="https://www.declara.com/" target="_blank">Declara </a>is an intelligent social learning platform - Fo<a class="g-profile" href="http://plus.google.com/104843626004337403547" target="_blank">+Ramona Pierson</a> and <a class="g-profile" href="http://plus.google.com/104443809038066974023" target="_blank">+Nelson Gonzalez</a> the products has the advanced analytics that helps understand how people learn, what content they use or generate, and which peers and mentors help them the most. Insights from these analytics help in improving the learning and also enable content providers to refine their products and organizational leaders to make smarter decisions. <span style="color: #274e13;"><b>As people learn, Declara learns! </b></span><br />
<br />
<h3>
<om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram"><br /></om></om></om></om></om></om></om></om></om></om>
<om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram"><br /></om></om></om></om></om></om></om></om></om></om>
<om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram"><span style="color: red;">How to Predict a Best Seller (Book) Algorithmically</span></om></om></om></om></om></om></om></om></om></om></h3>
<br />
<br />
Analytics can help the publisher identify a best seller from the language and style of the writing (from the manuscripts)<br />
<br />
<br />
According to a recent research by Association of Computational Linguistics, the writing style of books was correlated with the success of the book.
The researchers used a process called <span style="color: blue;"><strong>statistical stylometry</strong></span>, a statistical analysis of literary styles in several genres of books and identified characteristic stylistic elements more common in successful tomes than unsuccessful ones.<br />
<br />
<h3>
<span style="color: blue;">Sentiment Analysis To Determine bias in Articles / Publications of an Author</span></h3>
<br />
Its seldom possible to be neutral as a journalist. We all have some bias for / against someone / something or some corporation. <a class="g-profile" href="https://plus.google.com/104454076541900497583" target="_blank">+Rami Nuseir</a> in his article on <a href="http://smartdatacollective.com/raminuseir/191466/strange-uses-sentiment-analysis?utm_source=hootsuite&utm_medium=twitter&utm_campaign=hootsuite_tweets" target="_blank">Strange uses of Sentimental Analysis</a> explains the use of technique to identify the bias of an author based on previous articles. A plugin created using <a class="g-profile" href="https://plus.google.com/103160806269070637663" target="_blank">+Semantria</a> analyses previous works of an author and scores the same based on their neutrality. This prediction helps the reader to identify the correct material<br />
<br />
<br />
<br />
<br />
<br />
<om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram"><br /></om></om></om></om></om></om></om></om></om></om>
<om name="Om Ganeshaya Namaha"><om name="Om Satguru Seshadri Swamigal Thiruvadike"><om name="Om Varahi Namaha"><om name="Om Saravana Bhava"><om name="Om Sai Ram"><om name="Om Namah Shivaya"><om name="Om Shakthi"><om name="Om Namo Narayana"><om name="Hari Om!"><om name="Jai Shri Ram"><br /></om></om></om></om></om></om></om></om></om></om>Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-78798366102046294782013-09-21T21:00:00.001-07:002013-09-21T21:00:41.936-07:00Supply Chain Analytics in Retail World<b><span style="color: red; font-size: large;">How Supply Chain Analytics is improving the efficiency in Retail World</span></b><br />
<br />
Retail Supply Chain is one of the most critical one. There has always been continuous improvement in Supply Chain efficiency by the retailers using various tools<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhaAzP3ahn4h5161TlAF7xDQLS6TO1SO1To6Bg5TD45lWRnYsf4rKg4i2jTWVo6F9Sk-uarRSRR8ehpOV664r1SE20a-pjL1NUB91bZaAy63FCwWA6V_ZAPdM_rw8dPkfVm4JcTbkrTs1o/s1600/Urban+Outfitters.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="256" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhaAzP3ahn4h5161TlAF7xDQLS6TO1SO1To6Bg5TD45lWRnYsf4rKg4i2jTWVo6F9Sk-uarRSRR8ehpOV664r1SE20a-pjL1NUB91bZaAy63FCwWA6V_ZAPdM_rw8dPkfVm4JcTbkrTs1o/s320/Urban+Outfitters.jpg" width="320" /></a>Supply chain analytics helps the retailer understand and predict it much before<br />
<span style="color: blue;"><br /></span>
<b><span style="color: blue;">Ticketing Supply Lead Time - Urban Outfitters</span></b><br />
<br />
US-based fashion and lifestyle retailer, Urban Outfitters, has been named as an early adopter of a new web-based analytics product designed to provide detailed visibility into variable ticketing supply lead times.
<br />
<br />
FastTrak Analytics is an internet-based software package for order processing, tracking and management of the ticketing function developed by <a class="g-profile" href="http://plus.google.com/111553539952303795103" target="_blank">+Fineline Technologies</a><br />
<br />
The new analytical reporting tool will provide Urban Outfitters and FineLine’s base of 200 brand name retail customers with three core reports:<br />
<br />
<b>order turnaround time</b>, which calculates the average time between receipt of an order by FineLine and shipment of tickets;<br />
<b>order received time</b>, as the average time between receipt of an order by FineLine and delivery of tickets to vendors;<br />
<b>orders shipped to country</b>, as the average time between receipt of an order by FineLine and delivery of tickets to vendors in a specific country.<br />
<br />
<br />Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-25202508840632168752013-09-15T09:22:00.001-07:002013-09-15T09:22:06.120-07:00Next Best Action and A/B Testing <b><span style="color: red; font-size: large;">How to use A/B Testing for Customer Analytics</span></b><br />
<br />
Next Best Action is a learning based on the response of the previous action. Every action/offer is an test offer.<br />
<br />
<b>A/B split testing</b><br />
<br />
A/B Tests work like this. Say Two different email messages (Message A / Message B) are sent to customer segments and the responses are measured by the following factors<br />
<br />
Mail Open<br />
Clicks on Links<br />
Conversion (Purchase etc)<br />
<br />
If say the more number of Message As are clicked than Message B, then A is said to be more effective.<br />
<br />
<b><span style="color: red;">Email Response analysis </span></b><br />
<br />
The responses are then analysed - responders / non-responders are segmented and analysed. The model is then refreshed.<br />
<br />
Once the model is refreshed the customers can be retargeted / left alone<br />
<br />
<b><span style="color: red;">Retargeting Customers</span></b><br />
<br />
Retargeting is to try out the offer / promotion / message another time. They can send the same message / a different customized message<br />
<br />
<br />
<span style="color: blue;"><b>A/B Testing in Web Page Design / Website Traffic</b></span><br />
<br />
<a href="http://www.sitedoublers.com/img/ab-testing-victorias-secret.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="237" src="http://www.sitedoublers.com/img/ab-testing-victorias-secret.png" width="320" /></a>A/B testing in websites use different web page content on version A and version
B of a page. The pages are loaded randomly to the user. The responses / conversions are analyzed. Next Best Action is defined for each page and the conversion rate is nothing but the rate of action being taken for the total visits. Some of these might be different design for version A and B or different positioning of elements etc<br />
<br />
<br />
<span style="color: red;"><b>Case Study - Victoria Secret A/B Testing</b></span><br />
<br />
Victoria Secret - the leading eCommerce vendor is testing its<br />
<br />
Email Subject lines<br />
Offer and Image<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
using A/B testing (see <a href="http://www.sitedoublers.com/blog/multivariate-test-victorias-secret" target="_blank">Site Doublers</a> for the complete case study)<br />Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-49762924840148656002013-08-19T03:36:00.000-07:002013-08-19T04:37:49.854-07:00Web Analytics - Repeat Customers<a href="http://2.bp.blogspot.com/-2H150IAUTHw/UR4mSehji-I/AAAAAAAAACM/3lsVDZos5Bs/s1600/online+fashion+shopping.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="196" src="http://2.bp.blogspot.com/-2H150IAUTHw/UR4mSehji-I/AAAAAAAAACM/3lsVDZos5Bs/s320/online+fashion+shopping.jpg" width="320" /></a><a class="g-profile" href="http://plus.google.com/115209321914160323553" target="_blank">+Adobe</a> report shows that repeat customers who are 8% of the ecommerce traffic contribute 41% of the sales. <br />
<br />
<strong><span style="color: blue;">Sale by 1 Repeat Customer = 11 times x Sale by New Customer</span></strong><br />
<br />
<a class="g-profile" href="http://plus.google.com/104079255913915128656" target="_blank">+Econsultancy</a> shows that the sales of the customers increased by the repeat of the visits<br />
<br />
<strong><span style="color: blue;">Sales by Second Time Customer = 3 times x Sale by First Customer</span></strong><br />
<br />
Going by all these metrics its imperative that repeat customers are a Golden Goose. How to keep the customers / make the customers buy again?<br />
<br />
<strong><span style="color: red;">Connecting with Customers</span></strong><br />
<br />
Retailers (Online/Offline) need to have constant touch with the customers. They would need to send relevant offers/messages (what is called as <a href="http://analyticsdud.blogspot.in/2012/12/what-are-steps-in-nbo-next-best-offer.html" target="_blank">Next Best Action</a> today) at right time through <a href="http://analyticsdud.blogspot.in/search/label/Right%20Channel" target="_blank">right channel</a><br />
<a class="g-profile" href="http://plus.google.com/114940515213690936534" target="_blank">+Yebhi India</a> is an example of badly managed customer interaction. The marketing team bombards the customers with Text Messages / EMails so that the customer blocks the sender / trashes the message once it lands in her phone<br />
<br />
A good marketing should take care of the Context and the customer's purchasing power/ intention into account before sending him/her the message<br />
<br />
Companies like <a class="g-profile" href="http://plus.google.com/109769941055589050900" target="_blank">+Store Express</a> etc provide ecommerce consultancy in this area. <a class="g-profile" href="http://plus.google.com/100296114230478191916" target="_blank">+IBM</a>'s <br />
<a href="http://www-03.ibm.com/software/products/us/en/digital-analytics/" target="_blank">Digital Analytics</a> has powerful analytics tools that can help to create, measure and monitor key metrics<br />
<br />
One of the primary channel nowadays is Mobile <a href="http://annaslinens.com/" target="_blank">Anna's Linens is</a> optimizing its ecommerce site for Mobile devices. The Omni-channel approach where the customers to store coupons on the mobile site and transferring back and forth to ecommerce or instore purchases is gaining momentum<br />
<br />
<br />Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-19534708515426803462013-07-04T05:07:00.000-07:002013-09-01T07:01:11.650-07:00Location Based Predictive Analysis using Crowd/Social Data - Traffic Congestion Analytics / Parking Space Analytics<strong><span style="color: red; font-size: large;">How to use Social/Location data for Big Data Analytics / Real-Time analytics</span></strong><br />
<strong><span style="color: red; font-size: large;"></span></strong><br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMuJ7N1FDYBKPPkx5Jx7-WShKp8yP_12TQfAi-BpyqESsp2ZfjOxF-K3Nh5kFM5psrxTVsUpDYklYd4K0dso0XOWNFTfXIdxpsdgvujnYlxhFTLMer7kAnW3tPTWHqi6x1Jll2rdd-ysk/s660/Parko+PArking+App.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMuJ7N1FDYBKPPkx5Jx7-WShKp8yP_12TQfAi-BpyqESsp2ZfjOxF-K3Nh5kFM5psrxTVsUpDYklYd4K0dso0XOWNFTfXIdxpsdgvujnYlxhFTLMer7kAnW3tPTWHqi6x1Jll2rdd-ysk/s200/Parko+PArking+App.png" width="102" /></a><br />
The real use of Analytics is slowly emerging. This time let's review some Mobile Apps build using <a class="g-profile" href="http://plus.google.com/104629412415657030658" target="_blank">+Android</a>, Apple and <a class="g-profile" href="http://plus.google.com/112433365121400733568" target="_blank">+Windows Phone</a><br />
<br />
<a href="http://www.parko.co.il/index.php?lang=eng" target="_blank">Parko</a> - an App to find the Parking spot uses the user's mobile behaviour and predicts when the user will vacate the spot and alerts the other drivers who have registered. The behavioural analytics is the USP of Parko<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjIZiCSYPi_8-kkY5w4Mcib5LXXt1N7P8qA9fO3iCcBKVHMK9WRy06jQGmCtWl_7WmZczace0JdZLx2lcREPCuDVeO7HLVQnusKlUokPCqan6kf9ODDc2iAweC7qwx01kto6jGGAIcWzI8/s225/Waze+Logo.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjIZiCSYPi_8-kkY5w4Mcib5LXXt1N7P8qA9fO3iCcBKVHMK9WRy06jQGmCtWl_7WmZczace0JdZLx2lcREPCuDVeO7HLVQnusKlUokPCqan6kf9ODDc2iAweC7qwx01kto6jGGAIcWzI8/s200/Waze+Logo.jpg" width="200" /></a><br />
<a class="g-profile" href="http://plus.google.com/112705110135772710409" target="_blank">+Waze</a> - that was recently acquired by <a class="g-profile" href="http://plus.google.com/102906181004577789365" target="_blank">+Google, Inc.</a> uses real-time information from nearby drivers to find the best path. It is basically a <span class="st">GPS-based navigational app which uses turn-by-turn navigation and the historical user-submitted travel times and route details</span><br />
<br />
The <a class="g-profile" href="http://plus.google.com/116947143125836691157" target="_blank">+Traveling Salesman</a> algorithm can be tested here.<br />
<br />
Real-time analytics need Big Data infrastructure where companies like <a class="g-profile" href="http://plus.google.com/107028439431690292784" target="_blank">+Cloudera</a> and <a class="g-profile" href="http://plus.google.com/116844353243787361742" target="_blank">+Hortonworks</a> play a key part. With Internet of Things gaining popularity the Apps will be replaced by the Cars itself. Some models from <a class="g-profile" href="http://plus.google.com/111107247010391604984" target="_blank">+Ford Motors</a> have the chips that can be used to relay Vehicle information to a central repository, which can be instantaneously mined and their insights reported/shared.<br />
<br />
This also needs a co-ordinate approach from the government / local body. The results from the analytics is not just for the drivers - it can help the Local police plan Signals appropriately, the Schools and Hospitals can plan their routes.<br />
<br />
Location based analytics also involves predicting the behaviour of the user based on his/her current navigation. <br />
<br />
<span style="color: red;"><strong>Geo Fencing in Marketing </strong></span><br />
<br />
Geofencing is the new buzzword for location based marketing. The success of FourSquare has led to location based analytics and marketing. Location based marketing needs to take care of <br />
<br />
<ul>
<li>Delimiting Geofencing Perimeter</li>
<li>Analyze Perimeter Segments</li>
<li>Data Integration (Location with Transactional and Customer data)</li>
<li>Location sensitive content / message / offer creation</li>
<li>Privacy Filtering </li>
<li>Location based Delivery </li>
</ul>
<br />Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-73891956028242794422013-06-11T22:51:00.004-07:002014-11-13T21:58:02.578-08:00Customer analytics from Anonymous In-Store Customers (In-Store Shopper Analytics)<strong><span style="color: #cc0000; font-size: large;">How to Perform Data Analysis on Anonymous Customers who have Purchased In-Store with Cash</span></strong><br />
<br />
Customers who shop irrespective of whether they have loyalty card leave a trail during payment, Their Credit Card Data stores vital information and can be used for subsequent analysis (<a href="http://analyticsdud.blogspot.in/2013/03/payment-card-industry-crucial-for-real.html"><span style="color: #cc6611;">Payment Card Industry - Crucial for Real-Time Next Best Action (NBA) - Big Data</span></a>)<br />
<br />
<br />
<strong><span style="color: #cc0000;">How to Track Anonymous Customers</span></strong><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhSPUvxY5UoiXgQ-NSvGiODL89A8rSRj2yx6swjX8OXiB1LILDHB30fu9E6xf6q_a8VGs661bbAB7KYOHx9osAGE44YaFrsGDjFLPvmibm5E67mQV01VsifED2J8jSch39Y-n1b5piVQqk/s1600/ibm_logo.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhSPUvxY5UoiXgQ-NSvGiODL89A8rSRj2yx6swjX8OXiB1LILDHB30fu9E6xf6q_a8VGs661bbAB7KYOHx9osAGE44YaFrsGDjFLPvmibm5E67mQV01VsifED2J8jSch39Y-n1b5piVQqk/s200/ibm_logo.jpg" height="95" width="200" /></a>Tracking Anonymous customers (visitors) on the web is quite easy nowadays. The Cookies, IP<br />
Addresses etc provide a wealth of information and this can be used when the visitors return. Tools like <a href="http://www.sas.com/" target="_blank">SAS</a>, SPSS, <a class="g-profile" href="http://plus.google.com/100878824085031851878" target="_blank">+IBM Smarter Analytics</a> and Manthan Systems's <a href="http://www.manthansystems.com/en/products/arc-customer-analytics" target="_blank">ARC Customer Analytics</a> provide anonymous visitor behaviour analysis . <br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEinUgrGpUUz_XAVJoXGVpki8dMkgqho_1qlGoL0lqCW_NQlV6zrKIYfEbTsABHz_7XkGwWvmFuSd2vYMDyQGMgrmylpKWka5EqnwzKrXosHIbqPhWUbTnK-DP9DYAIBKdkQMo2JnXuxcVo/s1600/logo-catalina.gif" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEinUgrGpUUz_XAVJoXGVpki8dMkgqho_1qlGoL0lqCW_NQlV6zrKIYfEbTsABHz_7XkGwWvmFuSd2vYMDyQGMgrmylpKWka5EqnwzKrXosHIbqPhWUbTnK-DP9DYAIBKdkQMo2JnXuxcVo/s1600/logo-catalina.gif" /></a>How about Anonymous Customer <strong>in Store</strong> and analysing their behaviour. Companies like <a href="http://www.catalinamarketing.com/home.php" target="_blank">Catalina</a> uses the information of buying preferences of customers to drive promotions, merchandizing and sales. Catalina claims their data and insights are unique. <br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjfKRNneyi93hd1LvgKisOS_2cgMfUhjIulm_OjV2Nc1CDmQwbx04O1BQogxfvpY6kzlU4n8XSZpsNgVicz1EBH-mNIgRHQMQs3UQpiD2mUvV46O4Il4TofSnt13T6Ed4oX3ogWhjPfrBM/s1600/RetailNext-logo.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjfKRNneyi93hd1LvgKisOS_2cgMfUhjIulm_OjV2Nc1CDmQwbx04O1BQogxfvpY6kzlU4n8XSZpsNgVicz1EBH-mNIgRHQMQs3UQpiD2mUvV46O4Il4TofSnt13T6Ed4oX3ogWhjPfrBM/s200/RetailNext-logo.png" height="103" width="200" /></a>Aggregate data from Customers provide rich information about Brand Preferences etc. <br />
<br />
<br />
Video Analytics is also common in Retail nowadays. RetailNext, uses video footage to study how shoppers navigate and pushes appropriate messages/promotions<br />
<br />
RetailNext also uses data to map customers’ paths.
What is interesting is the ability to differentiate men from women, and children from adults from anonymous data
<br />
<br />
<b>How it Works:
</b><br />
Most often the Analytics provider rely on <b>Wifi Pings</b>, the Shopper's phone when it searches for WiFi provided by the retailer, pings the Router and the Router captures the signal strength to identify the location
<br />
<br />
<a href="http://euclidanalytics.com/" target="_blank">Euclid Analytics</a> also uses WiFi data to understand the footfalls, the time spent at each aisle etc. Also it measures the signals between a smartphone and a Wi-Fi antenna to count how many people walk by a store and how many enter.<br />
<br />
<a class="g-profile" href="http://plus.google.com/106092229730683979920" target="_blank">+Cisco</a>'s Meraki wireless router has a feature called <a href="http://meraki.cisco.com/blog/2013/05/introducing-presence-integrated-location-analytics-and-engagement/" target="_blank">Presence</a>, which has a good location analytics dashboard that measures key <strong><span style="color: red;">anonymous visitor tracking metrics</span></strong> - Capture Rate , PasserBy, Visitors, Median Visit Length, Repeat Visitors etc.<br />
<br />
This information can be used for better in-store promotions, Point-of-Sale displays etc. Cisco Meraki has partnered with Facebook to provide Free WiFi in lieu for providing some information<br />
<br />
Amazon is testing its own WiFi network. Currently Amazon devices access the internet through its Whispernet service, which runs on AT&T’s 3G cellular network<br />
<br />
<strong><span style="color: blue;">Real-Time Customer Feedback</span></strong><br />
<br />
<span style="font-size: x-small;">Annik has launched ‘Rapid Insights’ specifically for companies who
operate retail stores and want to understand & track customer
feedback in real time. The real benefit of this solution lies in taking
corrective action in real time to improve overall customer experience.
This revolutionary technology is extremely user friendly and can be
implemented in retail stores easily. </span><br />
<span style="font-size: x-small;"><br />How it works? </span><br />
<span style="font-size: x-small;">-- Placing of tablet at the retail outlet with platform agnostic proprietary customer feedback module </span><br />
<span style="font-size: x-small;">-- During the retail journey, customer shares experience through tablet </span><br />
<span style="font-size: x-small;">-- The management accesses real-time dashboard to view customer feedback and take corrective action </span><br />
<br />
<span style="color: blue;"><b>Create Right Mood at Right Time using Experience Players </b></span><br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEieBpSl1tTF47Ir-68aILEF0ldMDkgIVaRBYbHIBgHbXIp_wvOnh99FBWCfU9cWe3jytPC1o_r4Tm0c4pcFh98F8gSnUUmgKbfBzJqBw_0t4szxo8504ZnwtZzHvVSNzfbASyTfA07kEpE/s1600/Phillips+Retail+Solutions+-+Experience+Player.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEieBpSl1tTF47Ir-68aILEF0ldMDkgIVaRBYbHIBgHbXIp_wvOnh99FBWCfU9cWe3jytPC1o_r4Tm0c4pcFh98F8gSnUUmgKbfBzJqBw_0t4szxo8504ZnwtZzHvVSNzfbASyTfA07kEpE/s320/Phillips+Retail+Solutions+-+Experience+Player.jpg" height="68" width="320" /></a></div>
Customers doesn't come for Price/Offers, they come for good customer experience, which is why the retailer need to create Right Mood at Right time. <a href="http://www.retailsolutions.philips.com/content/platform.html" target="_blank">Philips Retail Solutions (PRS)</a> helps retailer create memorable in-store experiences with its Experience Player (EP). EP is a clever little black box that allows one to control individual experiential assets, whether it be animated on-screen content, atmospheric light levels or audio. The player can be scripted or programmed with a sequence of events within a set timeline. This solution is ideal for a Garment boutique or Clothes Retailer<br />
<br />
<h3>
<b><span style="color: red;">iBeacon and LTE Direct</span></b></h3>
<br />
With more devices on Customer's hands, getting their attention becomes a top priority when they are inside / near the stores<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEibHNDFtXEA37K0IlyFtgG-rDTeudgsjIMykICNOglR7ixm2slYZ12uKFFrdh9HdiSnEY8kQQUye0GGBPmk0572fooSOh6kU5jv_ttOb4j6QiEOfu0MEQwzFdmEzquh8O5qVhScTinb4es/s1600/apple-store-ibeacon.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEibHNDFtXEA37K0IlyFtgG-rDTeudgsjIMykICNOglR7ixm2slYZ12uKFFrdh9HdiSnEY8kQQUye0GGBPmk0572fooSOh6kU5jv_ttOb4j6QiEOfu0MEQwzFdmEzquh8O5qVhScTinb4es/s320/apple-store-ibeacon.jpg" /></a></div>
<b>iBeacon</b><br />
Apple's new mobile notifications system iBeacon is being touted by big brands as the next great opportunity in advertising. Using tiny Bluetooth wireless transmitters affixed to buildings, iBeacon lets companies send iPhone owners specific pop-up notifications based on their location and proximity to stores and products. These iBeacon transmitters need not be a separate device but some of these transmitters are simply iPhones as iPads running iOS 7, which lets these device act as both iBeacon transmitters and receivers
<br />
<br />
<b>LTE Direct</b><br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgp_7Q97KMzVYbnNnxT9FqRs_Di8r9qUXENLcoUZg_YX2SCU04IEcfdrep2a6lIp6plg-3uJu7j8H8pyHbKCyCnk1I0flUKYCfPKQBXiu5ZTPNYoDbobFhMNdWRdFTPZbz2TjO8f5mcBMg/s1600/Qualcomm+LTE+Direct.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgp_7Q97KMzVYbnNnxT9FqRs_Di8r9qUXENLcoUZg_YX2SCU04IEcfdrep2a6lIp6plg-3uJu7j8H8pyHbKCyCnk1I0flUKYCfPKQBXiu5ZTPNYoDbobFhMNdWRdFTPZbz2TjO8f5mcBMg/s1600/Qualcomm+LTE+Direct.jpg" height="224" width="320" /></a><a class="g-profile" href="https://plus.google.com/112709817520334775333" target="_blank">+Qualcomm</a>'s LTE Direct technology is touted as an alternative to iBeacon because of the Privacy it brings. LTE Direct is a device to device platform (synchronous) that helps proximity detection apps in battery efficient manner.<br />
Its discovery is connectionless and is only based on proximity, allowing the devices to discover others without revealing their own identity or exact location. Devices in proximity read the 'expressions' for determining the relevance of one another. This is meant for the <b>autonomous discovery</b><br />
<br />
Fabric is the product of Powered Analytics, Inc., aiming to bring an Amazon-like shopping experience into the physical store. Fabric works using Beacon technology - it learns the store floormap and tags products and categories with their location in-store. Integrating the application with Web and Mobile applications (Apps) would ensure that the shoppers are tracked across channels, and their location is used to predict the right product at the right time across channels<br />
<br />
This way In-Store (Brick & Mortar) customers can be delighted by leveraging the data from their online experience and vice-versa<br />
<br />Unknownnoreply@blogger.com1tag:blogger.com,1999:blog-1872026853745700770.post-86616753476870872662013-06-08T06:48:00.001-07:002013-06-08T06:48:05.926-07:00Read then Follow Now - How to Chose Right Channel - Using Social Media Analytics <strong><span style="color: red; font-size: large;">Derive Customer Insights from Social Media Information by Big Data Analytics</span></strong><br />
<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMU8Z8sMkjif6eBu2KeHHo3hebYlU_-qjZ6nL0bqcyPtb84Tmp4cfmFXiUJaO6niBO_DW-FLtglSlUJHq3hf5a_ENkqxhbRA35BYix6DyhEBTY2fOW9guNfE2NxkasluPjQsKOOxsj9lI/s1600/Twitter.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMU8Z8sMkjif6eBu2KeHHo3hebYlU_-qjZ6nL0bqcyPtb84Tmp4cfmFXiUJaO6niBO_DW-FLtglSlUJHq3hf5a_ENkqxhbRA35BYix6DyhEBTY2fOW9guNfE2NxkasluPjQsKOOxsj9lI/s200/Twitter.png" width="186" /></a>Not so long before people (or customers) read newspapers, browsed magazines, visited libraries . Then came Web - people browsed, then came the <a class="g-profile" href="http://plus.google.com/115896680450665815587" target="_blank">+Amazon Kindle Fire</a> a Book library in your hands. Now it's an era of Social Media where <a class="g-profile" href="http://plus.google.com/107350354213838732087" target="_blank">+LinkedIn</a> , <a class="g-profile" href="http://plus.google.com/109594653289822557717" target="_blank">+Twitter</a> and <a class="g-profile" href="http://plus.google.com/109670898846729799323" target="_blank">+Facebook </a>have made them as <strong><span style="color: blue;">Followers!</span></strong><br />
<strong></strong><br />
Yes people follow a lot - <a class="g-profile" href="http://plus.google.com/108227564341535363126" target="_blank">+The Boston Globe</a> , and <a class="g-profile" href="http://plus.google.com/101169269861152216375" target="_blank">+Bloomberg News</a> is available on Twitter and Facebook. You can subscribe, follow them . You can follow <a class="g-profile" href="http://plus.google.com/108803539780596310930" target="_blank">+CIO</a> , <a class="g-profile" href="http://plus.google.com/103037366582313115962" target="_blank">+TechCrunch</a> if you are a technology geek. If you are a marketer then <a class="g-profile" href="http://plus.google.com/106826710567191382794" target="_blank">+marketingprofs</a> might be in your following list, <a class="g-profile" href="http://plus.google.com/111647990267476504720" target="_blank">+Nike</a> and <a class="g-profile" href="http://plus.google.com/101842039723189178420" target="_blank">+adidas</a> will be for a Sports geek<br />
<br />
So what these tells us .. in the first place it gives some understanding about the customer's behaviour. Why is this so important for any marketer.<br />
<br />
<strong><span style="color: red;">Social Media, Marketing and Segmentation</span></strong><br />
<br />
Marketers now use Social media extensively for communicating with their customers. They also use the massive volume of Tweets, Likes to get more insights about the customer.<br />
<br />
A simple analysis carried out by a Watch manufacturer shows that those who have bought their premium watches are followers of GeorgeMichael (<a class="g-profile" href="http://plus.google.com/106339294442493123388" target="_blank">+GEORGEMICHAELORG GMORG</a>) Is it time to tap them?<br />
<br />
<span style="color: blue;">How to Merge Social and Customer Data</span><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh4lV3LZ4JzIV__hHH2Nq_rvSls_rbobpczr6cS_Uh2D-wUl4YK8q6fGYAZNJO0VEwIpBtgC9eEy5jFdYkS2t2RnG1XeNZjDwX2JI2GbuLeKsWwlku2FtrRPUyTGdAyfuJdxshZ3U8VYQA/s1600/HortonWorks+Logo.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh4lV3LZ4JzIV__hHH2Nq_rvSls_rbobpczr6cS_Uh2D-wUl4YK8q6fGYAZNJO0VEwIpBtgC9eEy5jFdYkS2t2RnG1XeNZjDwX2JI2GbuLeKsWwlku2FtrRPUyTGdAyfuJdxshZ3U8VYQA/s1600/HortonWorks+Logo.png" /></a>Clustering or <a href="http://analyticsdud.blogspot.in/2013/02/segmentation-standards-framework.html" target="_blank">Segmentation</a> of the data using a combination of Customer, Transactional and Social data is beneficial as it will find homogenous groups. <br />
<br />
To arrive at the point - Social media data needs to be aggregated. This is where Big Data comes into picture (Refer <a href="http://analyticsdud.blogspot.in/2013/05/how-is-apache-hadoop-using-big-data.html"><span style="color: #cc6611;">How is Apache Hadoop used Big Data Analytics and Inteligence </span></a>). Companies like <a class="g-profile" href="http://plus.google.com/116844353243787361742" target="_blank">+Hortonworks</a> , <a class="g-profile" href="http://plus.google.com/111552380898436204189" target="_blank">+Cloudera Inc</a> provide Hadoop clusters where Social media data can be crunched to get the relevant information out.<br />
<br />
<br />
Here care must be taken to include/excluded Social data as segmentation variable as it has huge potential to skew the result<br />
<br />
Social media information can be used either as :<br />
<br />
<ul>
<li>Segmentation Variable</li>
<li>Interpretation variable</li>
</ul>
The cluster profiling would reveal the impact of the social data. For example, a Retailer found that customers who retweet have constantly responded to a type of promotion. Share your own experiences<br />
<br />
<br />
<br />
See also<br />
<a href="http://analyticsdud.blogspot.in/2013/04/how-to-segment-social-media-users.html"><span style="color: #cc6611;">How to Segment Social Media Users (Influencers / Detractors / Recommenders)</span></a><br />
Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-11202704640408816542013-05-29T06:57:00.000-07:002013-05-29T08:17:07.012-07:00How is Apache Hadoop used Big Data Analytics and Inteligence <br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEifFZB0mnkOYf0gfw7SqgUAi4ZPrZyiEGHLsdSPFRjMI2P8Yksq3Py68Rmdnp9jrz1fuOu78dC2_MRJgLFHS69Vgtlq71mALXbDZCsVa9Y08o0y-Zf9DkjAGV5KMkfP7fhYxp2MlIbLOAo/s1600/HortonWorks+Logo.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEifFZB0mnkOYf0gfw7SqgUAi4ZPrZyiEGHLsdSPFRjMI2P8Yksq3Py68Rmdnp9jrz1fuOu78dC2_MRJgLFHS69Vgtlq71mALXbDZCsVa9Y08o0y-Zf9DkjAGV5KMkfP7fhYxp2MlIbLOAo/s200/HortonWorks+Logo.png" width="200" /></a><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjl9sT0-WomdceRUoYWpHqqPT5DaeaPDNTfekprZFMfRIgcJitfCT1RsHQl6FTqGpf5apQRKmaFCmFlqQ_796PFWKaY31WOoeH3p9MVrBHxK5T6g0OlRjb-O2BhEEyRNelcQqELTxQM9VM/s1600/Big+Data+-+Apache+Hadoop+-+Patterns+of+Use.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjl9sT0-WomdceRUoYWpHqqPT5DaeaPDNTfekprZFMfRIgcJitfCT1RsHQl6FTqGpf5apQRKmaFCmFlqQ_796PFWKaY31WOoeH3p9MVrBHxK5T6g0OlRjb-O2BhEEyRNelcQqELTxQM9VM/s320/Big+Data+-+Apache+Hadoop+-+Patterns+of+Use.png" width="320" /></a><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEifFZB0mnkOYf0gfw7SqgUAi4ZPrZyiEGHLsdSPFRjMI2P8Yksq3Py68Rmdnp9jrz1fuOu78dC2_MRJgLFHS69Vgtlq71mALXbDZCsVa9Y08o0y-Zf9DkjAGV5KMkfP7fhYxp2MlIbLOAo/s1600/HortonWorks+Logo.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><span style="color: red; font-size: large;"><strong></strong></span></a><span style="color: red; font-size: large;"><strong>Big Data Analytics - Usage of Apache Hadoop / What is the use of Apache Hadoop in an Analytical Project</strong></span><br />
<br />
There are various ways Apache Hadoop is used in a Big Data Project. <a class="g-profile" href="http://plus.google.com/116844353243787361742" target="_blank">+Hortonworks</a> latest report <br />
<div class="r">
<a href="http://hortonworks.com/blog/apache-hadoop-patterns-of-use-refine-enrich-and-explore/">Apache <span style="font-size: small;">Hadoop</span> <em>Patterns of Use</em>: Refine, Enrich and <b>...</b> - <em>Hortonworks</em></a> categorizes it into</div>
<ul>
<li><div class="r">
Data Refinery Pattern</div>
</li>
<li><div class="r">
Data Exploratory Pattern</div>
</li>
<li><div class="r">
Application Enrichment Pattern</div>
</li>
</ul>
In <strong><span style="color: red;">Data Refinery</span></strong> - Hadoop is used for Cleansing up the data and sending the output (probably as aggregation / refinement) to the Enterprise Data Warehouse which might be <a class="g-profile" href="http://plus.google.com/115607918987921226255" target="_blank">+Oracle</a> <a class="g-profile" href="http://plus.google.com/117929808612372043364" target="_blank">+SQLServer</a> etc<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiEcarm17B4E6BQtZbdhBSQnT6h896V3PMsbRS04Ynk-cmpF3NRIaaxyA7q50646-C59P0RxLV8Z8Orldoipp6GuC8-Y_0Z1MkSBLebvBrgxCoZED_vEUenfZZ8GG3pfoBqNtxHSwp5RQo/s1600/Big+Data+-+Apache+Hadoop+-+Patterns+of+Use+-+Data+Exploration.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiEcarm17B4E6BQtZbdhBSQnT6h896V3PMsbRS04Ynk-cmpF3NRIaaxyA7q50646-C59P0RxLV8Z8Orldoipp6GuC8-Y_0Z1MkSBLebvBrgxCoZED_vEUenfZZ8GG3pfoBqNtxHSwp5RQo/s320/Big+Data+-+Apache+Hadoop+-+Patterns+of+Use+-+Data+Exploration.png" width="320" /></a></div>
In <strong>Data Exploration pattern</strong> - data is analysed in Hadoop environment, using Hive etc. and the results are shared with the Applications. There are many Big Data Visualization Tools that provide good reports. There are some Open Source tools like Pentaho Business Intelligence Studio that offers Big Data Visualization and Reports<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhfUbcoJGcYhKzxCPWbLK8-6YtWCL_YB8KfIE0NefufHwvXkBGNGu7MTnJZpxtMdE80s_Hyqe4w18KCVoaF1gFjEtK8CAm2OLgwwnBJU_8HtxaIW_ot8C0_NPqM_lBRCXSiiZLXw3_jnZc/s1600/Big+Data+-+Apache+Hadoop+-+Patterns+of+Use+-+App+Enrichment.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhfUbcoJGcYhKzxCPWbLK8-6YtWCL_YB8KfIE0NefufHwvXkBGNGu7MTnJZpxtMdE80s_Hyqe4w18KCVoaF1gFjEtK8CAm2OLgwwnBJU_8HtxaIW_ot8C0_NPqM_lBRCXSiiZLXw3_jnZc/s320/Big+Data+-+Apache+Hadoop+-+Patterns+of+Use+-+App+Enrichment.png" width="320" /></a>In <strong>Application Enrichment Pattern </strong>the entire data is stored in Apache Hadoop. For example, the Web session is stored in Hadoop and appropriate actions are taken based on the user's web navigation
.<br />
<br />
<br />
These are some broad classification of the use of <a class="g-profile" href="http://plus.google.com/102013639764496090501" target="_blank">+Apache Hadoop</a>Unknownnoreply@blogger.com4tag:blogger.com,1999:blog-1872026853745700770.post-6337766747946160812013-05-29T04:22:00.000-07:002013-05-29T04:22:07.726-07:00Free Tools for Data MiningI got to know about RapidMiner and thought of testing it out (under progress). Tried K-Means clustering. The selection of raw data / input file was pretty easy, then I tried to link the process to K-means. +RapidMiner threw an error that there were some missing values (also suggested to select a method/process that is available for missing value imputation.<br />
<br />
I added the process (refer figure below) and then linked the process back to the +KMeans. So far so good. Wanted to know more from statisticians and analysts who have used <a href="http://analyticsdud.blogspot.in/2012/11/open-source-software-for-analytics.html" target="_blank"><span style="color: #cc6611;">Open Source Software - like R</span></a>, and also <a href="http://www.sas.com/"><span style="color: #cc6611;">SAS,</span></a> <a class="g-profile" data-gapiattached="true" data-gapiscan="true" data-onload="true" href="http://plus.google.com/115684033096930245910" id="___hovercard_0" target="_blank"><span style="color: #cc6611;">+Microsoft Dynamics ERP</span></a> and <a href="http://www.ibm.com/software/analytics/spss/" target="_blank"><span style="color: #cc6611;">SPSS</span></a> <br />
<br />
<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhq_M3MIlnkbszbgfKQeI0btY4vMFSZobz2CSxdYvVATWOBARqinXpFFiHPSJDStUB_bfzVUZ6JD5x3-cMX3nMR6iUwlVPaoOoKcYqZ8hnh6jpAMRU7WuWxH-hwAQ4ZosFULgufhGcRFgw/s1600/RapidMiner+Clustering+-+Free+Tool+for+Segmentation.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img height="336" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhq_M3MIlnkbszbgfKQeI0btY4vMFSZobz2CSxdYvVATWOBARqinXpFFiHPSJDStUB_bfzVUZ6JD5x3-cMX3nMR6iUwlVPaoOoKcYqZ8hnh6jpAMRU7WuWxH-hwAQ4ZosFULgufhGcRFgw/s640/RapidMiner+Clustering+-+Free+Tool+for+Segmentation.png" width="640" /></a></div>
Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-87430755805201863882013-05-27T00:37:00.002-07:002013-10-12T09:06:29.908-07:00Segmentation of American Teens Internet Usage<a href="http://images2.fanpop.com/image/photos/8500000/Secret-Life-Girls-secret-life-of-the-american-teen-8597479-594-396.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="213" src="http://images2.fanpop.com/image/photos/8500000/Secret-Life-Girls-secret-life-of-the-american-teen-8597479-594-396.jpg" width="320" /></a><br />
<br />
<b><span style="color: #274e13; font-size: large;">American Teens - Segmentation</span></b><br />
<br />
Smartphone adoption among American teens has increased substantially and mobile
access to the inter<a href="http://www.pewinternet.org/Reports/2013/Teens-and-Tech/Summary-of-Findings.aspx" target="_blank">Teens and Technology 2013</a> findings. <a class="g-profile" href="https://plus.google.com/111317905958703170091" target="_blank">+Teens of America</a> are +Hyperconnected<br />
net is pervasive by Pew Research Center's <br />
<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiKGKLmq1LbFXEFC5WbTHqJoPxQdv03ZgO555Wq7br__igHMnehQuAUKOEWrPicOF8tsxLgb51AxWaPwyAu0UFGhREVlTRzOzIw50C7KkUeTmUTEe4Etbb4R_ZpRH5nnH7wdAsnylqREPE/s1600/Analytics-Hyperconnected-Life-800.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiKGKLmq1LbFXEFC5WbTHqJoPxQdv03ZgO555Wq7br__igHMnehQuAUKOEWrPicOF8tsxLgb51AxWaPwyAu0UFGhREVlTRzOzIw50C7KkUeTmUTEe4Etbb4R_ZpRH5nnH7wdAsnylqREPE/s1600/Analytics-Hyperconnected-Life-800.jpg" /></a></div>
<br />
<br />
This also shows the predictions for 2020 by <a class="g-profile" href="https://plus.google.com/103750685293771924101" target="_blank">+Pew Research Center</a> and +Internet Provider.org<br />
<br />Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-26327180170179766492013-05-23T05:17:00.001-07:002013-08-19T07:19:48.177-07:00How to Measure Effectiveness of a Campaign using Marketing analytics (Banking)<span style="color: red; font-size: large;"><strong>Marketing Analytics - Measure Effectiveness of Email Campaign for Bank</strong></span><br />
<br />
<br />
In our <a href="http://analyticsdud.blogspot.in/2013/03/case-study-customer-analytics-for.html"><span style="color: #cc6611;">Case Study: Customer Analytics for Telecom Operator to Cross-Sell and Up-Sell</span></a> we had a look at the Telecom Analytics .. Now let's have a look at how Analytics has changed the communication between the bank and its customers<br />
<br />
Banks have a good understanding of customer as the customers part with various data points (SSN #, Tax #, Address, Employee, Salary etc.) at different points of time (Enrolment, Address Change, Mobile Banking etc..)<br />
<br />
This information is used for personalized marketing through email (This is the Channel for analysis - <a href="http://analyticsdud.blogspot.in/2013/03/what-are-key-channels-to-be-considered.html" target="_blank">multiple outbound channels</a> can also be fed) . <br />
<br />
<span style="color: blue; font-size: large;">Processes in Marketing Analytics for Personalized Promotions for Banking</span><br />
<br />
The processes involved are as follows<br />
<br />
1. Gather Data<br />
2. Analyze Data , Document Discovery and Create Model<br />
3 Execute Campaign <br />
4. Collect Responses<br />
5. Measure the Results (Efficiency)<br />
6. Fine tune / Optimize the model<br />
7. Refresh Model and Segment<br />
<br />
Since the necessary data for understanding the customer is already available / collected,<a href="http://analyticsdud.blogspot.in/search?q=segmentation" target="_blank"> the data is segmented</a> to understand different customer segments that are available and their profiles<br />
<br />
Each segmented is treated in unique way based on their behavioural patterns<br />
<br />
The segments are divided into control and test groups. The customers in the test groups are subjected to the personalized marketing campaign while the control segment customers are part of regular campaigns<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg1jRg1zlRzHOIJ7DEMi7ZK_wdNoon9ASS40Lu2reH7zm74wZSoUjPmbyHglVQWXDOdiSIz4uNEt_uLNiYCr12ZzUSocVTNoBKaC7kiB6ncDwIILQRHHDoVQCm6xJj6i7lVeoOkJ29VbiY/s1600/Email+Marketing+Effectiveness+Analysis+-+NBO.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" height="480" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg1jRg1zlRzHOIJ7DEMi7ZK_wdNoon9ASS40Lu2reH7zm74wZSoUjPmbyHglVQWXDOdiSIz4uNEt_uLNiYCr12ZzUSocVTNoBKaC7kiB6ncDwIILQRHHDoVQCm6xJj6i7lVeoOkJ29VbiY/s640/Email+Marketing+Effectiveness+Analysis+-+NBO.png" width="640" /></a></div>
<br />
<br />
The most important step after sending those mailers is to collect responses. This is a key differentiator between a good and bad campaign management<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhWp8A5eFKD3eS7niI_OeabDx1j2YaxBw_yyuDqLYJ3kplU2zLyBWjO7MlqLg0FUwMKGRTB1AJp8Bry75k5mH0Kgzmfk5Wa_-69XbBaNw14_zbXJ3aMTMrRfLOp0D62XK2-jAue5SRIq74/s1600/Email+Marketing+Effectiveness+Analysis+-+NBO+2.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhWp8A5eFKD3eS7niI_OeabDx1j2YaxBw_yyuDqLYJ3kplU2zLyBWjO7MlqLg0FUwMKGRTB1AJp8Bry75k5mH0Kgzmfk5Wa_-69XbBaNw14_zbXJ3aMTMrRfLOp0D62XK2-jAue5SRIq74/s320/Email+Marketing+Effectiveness+Analysis+-+NBO+2.png" width="320" /></a>The responses are subjected to Response Segmentation analysis and the results are measured. What are the parameters that are clearly visible in the responders? What are the feature of the non-responders .. this is an area where business needs to play some role rather than IT / Analysts<br />
<br />
The Bank's Personalized Campaign has created a 500% increase in response compared to the generic mailer (Refer Figure)<br />
<br />
The model is recreated with the understanding from the new findings - this is called Model Recalibration. The model is refreshed in campaign management system and the process continues<br />
<br />
<br />
<br />
The <a href="http://analyticsdud.blogspot.in/2012/12/what-are-steps-in-nbo-next-best-offer.html" target="_blank">Next Best Action</a> (here the Mailer) is a continuous learning process<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjTCY9WSC5qNoNSo5gFoAbtlFOmPhYnEZn9tDfxyXJjdwJwuiWKO2bFJQkS14VuJ5PIbM-T8l-VPzImkNYKFx8Df4Ci5HY1YRgxVZvMLrdS5goliUYvYLkxZm0811ATuoFAdxgLL4uIVlA/s1600/MicroSoft-Dynamics-Logo.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="110" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjTCY9WSC5qNoNSo5gFoAbtlFOmPhYnEZn9tDfxyXJjdwJwuiWKO2bFJQkS14VuJ5PIbM-T8l-VPzImkNYKFx8Df4Ci5HY1YRgxVZvMLrdS5goliUYvYLkxZm0811ATuoFAdxgLL4uIVlA/s320/MicroSoft-Dynamics-Logo.jpg" width="320" /></a><a class="g-profile" href="http://plus.google.com/115684033096930245910" target="_blank">+Microsoft Dynamics ERP</a> was used as the CRM for the Bank. Third party software was used for Mail blast and custom code was used for model development \<br />
<br />
<br />
There are also custom tools/solutions for campaign / personalized promotion. For example, <a href="http://www.blogger.com/www.manthansystems.com">Manthan Systems' </a>TargetOne tool uses data from various touch points like point-of-sale (POS) and store vicinity, during ecommerce transactions, email click-throughs and social media engagements to ensure right conversation is initiated with the right customer at the right time through the right medium<br />
<br />
See also:<br />
<a href="http://analyticsdud.blogspot.in/2013/03/payment-card-industry-crucial-for-real.html"><span style="color: #cc6611;">Payment Card Industry - Crucial for Real-Time Next Best Action (NBA) - Big Data</span></a> Unknownnoreply@blogger.com7tag:blogger.com,1999:blog-1872026853745700770.post-84602201691843779302013-05-20T04:12:00.000-07:002013-05-20T04:12:21.453-07:00How to Predict Employee Churn using analytics<span style="color: red; font-size: large;">How to Know if an Employee is going to Quit before he does</span><br />
<br />
Internal Spies! Yes this was one of the credible source of information. The spies are equipped with some extraordinary talent to grasp information from various sources / relate and then report / conclude (usually she/he leaves this to the boss)<br />
<br />
With Lean management .. the human source of information is trimmed and put into better use (really!)<br />
<br />
There are various data points that need to be captured to Analyse Employee Churn (We had already spoken a lot about Customer Churn in <a href="http://analyticsdud.blogspot.in/2013/03/customer-attrition-modeling-analytics.html"><span style="color: #cc6611;">Customer Attrition Modeling (Analytics)</span></a>)<br />
<br />
<ul>
<li>Current and Previous Appraisals (this might be a major source)</li>
<li>Current Pay ?(vis-à-vis Peers and Market)</li>
<li>Grievances / Issues Reported</li>
<li>Deviation in Time spent in Office</li>
<li>Frequency (change) of swipe pattern changes</li>
<li>Frequency (change) in access to internal information (Intranet etc.)</li>
<li>Job sites / Social Sites visit patterns (some offices have banned them)</li>
<li>Feedback from Peers</li>
<li>Feedback from Supervisors</li>
</ul>
This list will go on .. Social Media data ...<br />
<br />
Employee Churn is costly for the company. It takes months / years to replace the employee with a new one by adequate training etc<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="http://www.sumtotalsystems.com/_media/logos/sumtotal.svg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="75" src="http://www.sumtotalsystems.com/_media/logos/sumtotal.svg" width="320" /></a></div>
Thanks to data analysis, there are tools that help the companies to understand the employees, predict churn and help the manager in retaining the employee (that is the ultimate goal)<br />
<br />
SumTotal's Talent Management System is one such system that helps the HR <br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjPYb-GhTEKXAp0z3G4eeVQdJcM1zod_QG8KsxjMdDlWHjHgDrCmAa0QTr97p1IfkZSb9Q7JTqHRn51_KNRnnFymcTGcMrIWuRUJ_s_bWTwt0W8eVji_QF47a1JULmgVobky46ut_rVe94/s1600/UltiPro+Retention+PRedictor.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjPYb-GhTEKXAp0z3G4eeVQdJcM1zod_QG8KsxjMdDlWHjHgDrCmAa0QTr97p1IfkZSb9Q7JTqHRn51_KNRnnFymcTGcMrIWuRUJ_s_bWTwt0W8eVji_QF47a1JULmgVobky46ut_rVe94/s1600/UltiPro+Retention+PRedictor.jpg" /></a>Utlimate Software (<br />
<span class="irc_hd irc_iis"><a class="irc_hol irc_itl" data-ved="0CAQQjB0" href="http://www.ultimatesoftware.com/predict"><span class="irc_ho">www.ultimatesoftware.com</span></a>) has a tool called Retention Predictor<br />(TM) for predicting customer Churn<br />
<br /> </span><br />
<br />
Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-52883874061482334872013-05-20T03:35:00.002-07:002013-05-20T03:35:16.009-07:00How to Get Sales Leads from Analyzing Web Data<strong><span style="color: red; font-size: large;">Web Pattern Analysis for Identifying Prospects and Products</span></strong><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhd2NDQywq6UXxIRXaIwstQjxFfhdxEy5SvA52ZU699I4gh9Ec5FIdmCp6kOO5YRk6MRHTkWpz4BkNlj1S7BIEM1PZrrwsScL3RzZvJmzcCk5Tia1trVtbGFrrC-FXd0qok_G7tWI771qU/s1600/Infer+Palo+Alto+Rik+Singh.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhd2NDQywq6UXxIRXaIwstQjxFfhdxEy5SvA52ZU699I4gh9Ec5FIdmCp6kOO5YRk6MRHTkWpz4BkNlj1S7BIEM1PZrrwsScL3RzZvJmzcCk5Tia1trVtbGFrrC-FXd0qok_G7tWI771qU/s200/Infer+Palo+Alto+Rik+Singh.png" width="200" /></a><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi69A1ecsjql8rcD1bYM9Zd2e9vwrlg2thhwCxQlesRTmNBb5rdUv4HrhJxLdF-0Z-OXgcUFdkc1HNZ98RhjAvY557m2-Xd7WqSfVjnpilK6zSatF-j3ekWaiu6LDxvmMXO-1ebbBxDhG8/s1600/SalesForce.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="156" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi69A1ecsjql8rcD1bYM9Zd2e9vwrlg2thhwCxQlesRTmNBb5rdUv4HrhJxLdF-0Z-OXgcUFdkc1HNZ98RhjAvY557m2-Xd7WqSfVjnpilK6zSatF-j3ekWaiu6LDxvmMXO-1ebbBxDhG8/s200/SalesForce.jpg" width="200" /></a>Web is an abundant source of information. The trails left behind by online shoppers / browsers are as part of Web Log, Click Stream data etc.<br />
<br />
This data along with Social Media is fed to the Analytical model which analyses the trend and identifies potential customers / products that can be promoted<br />
<br />
There are many companies /retailers that are using Special algorithms / tools to crawl the web and derive useful insights.<br />
<br />
<br />
Some specialized companies like Palo Alto based Infer (<a href="https://www.infer.com/">https://www.infer.com/</a>) offer an analysis software that can be linked to CRM system like SalesForce (<a href="http://www.salesforce.com/)a">http://www.salesforce.com/)a</a> and rank the customer<br />
<br />
<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi7TxZGBLjRfSZtYrVZM8KWQ7uRAaiI6-AAZGS8K3Mj26vQCevvd7ncyhzKIUPoEiWFJy1QzeDaEc06ZL21oIAQ77p6yuAY7U2Td6Iu2-BwqHL8PSUNpq3ao8ugbpWMd9-uMXzyDCAFQnY/s1600/Twitter.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi7TxZGBLjRfSZtYrVZM8KWQ7uRAaiI6-AAZGS8K3Mj26vQCevvd7ncyhzKIUPoEiWFJy1QzeDaEc06ZL21oIAQ77p6yuAY7U2Td6Iu2-BwqHL8PSUNpq3ao8ugbpWMd9-uMXzyDCAFQnY/s200/Twitter.png" width="200" /></a>Infer's ranking system uses more than 150 signals , which includes many data feeds - Census, Job Boards, Tweets , Facebook Likes and Comments<br />
<br />
<br />
<br />
There are many algorithms that help in analysing the Facebook data<br />
<br />
<a href="http://developers.facebook.com/docs/opengraph/" target="_blank">OpenGraph API</a> is one of them<br />
<br />
<br />
See Also:<br />
<br />
<a href="http://analyticsdud.blogspot.in/2013/04/how-to-segment-social-media-users.html"><span style="color: #cc6611;">How to Segment Social Media Users (Influencers / Detractors / Recommenders)</span></a><br />
<br /><a href="http://analyticsdud.blogspot.in/2012/12/how-to-measure-price-sensitity-of.html"><span style="color: #cc6611;">How to measure Price Sensitity of Customers</span></a><br />
<br />
<a href="http://analyticsdud.blogspot.in/2013/02/segmentation-standards-framework.html"><span style="color: #cc6611;">Segmentation Standards / Framework</span></a>Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-59252750194814278182013-05-02T07:38:00.002-07:002013-05-02T07:38:48.832-07:00Payment Marketing Analytics - Something to Watchout in 2013<strong><span style="color: red; font-size: large;">How to Push Messages Real-Time at Point-of-Sale or Payment </span></strong><br />
<br />
Payment Marketing is catching up now. This provides the Bank / Retailer to push messages / offers on real-time to their customers.<br />
<br />
<strong><span style="color: #cc0000;">What is Payment Marketing?</span></strong><br />
<br />
Payment marketing is a mode of marketing using the Customer's payment card information and provide the customers with relevant offers / promotions etc. with the help of a layer built on top of the existing POS Terminals.<br />
<br />
We have already seen the importance of Payment card companies in the field of marketing. This is another layer of it<br />
<br />
<strong><span style="color: #cc0000;">How it Works?</span></strong><br />
<strong></strong><br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhEEUfZiv6PCJ7U746ZMe0EYrrDtc04LGspSZtYHNoRLl0nufbBHs8gHiyDmCMRa10a4GM59EAfeYUxbM_ZedeUU95hsjTdBsY2nrSy7oGQHYqF8UhyOY1EthToatHl3U4sisuGaZVUM0A/s1600/Payment+Marketing+Swipely.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhEEUfZiv6PCJ7U746ZMe0EYrrDtc04LGspSZtYHNoRLl0nufbBHs8gHiyDmCMRa10a4GM59EAfeYUxbM_ZedeUU95hsjTdBsY2nrSy7oGQHYqF8UhyOY1EthToatHl3U4sisuGaZVUM0A/s1600/Payment+Marketing+Swipely.jpg" /></a>The lifecycle of Payment Marketing revolves around understanding the customer through analytics. <a href="https://swipely.com/press/" target="_blank">Swipely</a>, a Payment marketing technology integrates with the payment network and collects data whenever the payment is made. The data is analysed and the insights are fed back to the marketing <br />
system, which can be used to <br />
<br />
<ul>
<li>Send Personalized Messages (Thank you message etc)</li>
<li>Cross-Sell products/Services</li>
<li>Inform corrective actions</li>
</ul>
<br />
The above can be expanded based on NBA strategy. The advantages of <a href="https://swipely.com/press/" target="_blank">Swipely</a> is the ease of upgrading - no hardware / software is required and no changes in customer's payment m<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjsF8ZyWhvvrIKx5qNK8-Fxu9XtG2qf8aD9tVXktpn-6ShcmocSZG3Mp61A4HBF8nJX0lOEEEMlr12rD-wV4aTJaPMu-q14B03TWADVWL-Yb99KJACUstKovAy7ub5vSOCuXjxOhQTvHKs/s1600/driveitnow_logo.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="74" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjsF8ZyWhvvrIKx5qNK8-Fxu9XtG2qf8aD9tVXktpn-6ShcmocSZG3Mp61A4HBF8nJX0lOEEEMlr12rD-wV4aTJaPMu-q14B03TWADVWL-Yb99KJACUstKovAy7ub5vSOCuXjxOhQTvHKs/s320/driveitnow_logo.png" width="320" /></a></div>
echanism<br />
<br />
<a href="http://www.driveitnow.net/" target="_blank">DriveItNow</a> uses the Credit, Criteria and Collateral to provide real payments<br />
<br />
<br />
<br />
<br />
<br />
<br />
Unknownnoreply@blogger.com1tag:blogger.com,1999:blog-1872026853745700770.post-3389393895542380902013-05-01T23:23:00.001-07:002013-05-01T23:23:17.547-07:00How does External Factors Affect Next Best Action (NBA) - Timely Promotions<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEibHtKyjH3YxHlpJiaN3EJ7sAWT4aZuUbhfKYcggXhCnAwl8OJp3FTq7BJaflyUbNEfkWgL17JZQS_visRnyfzPlljea9-9KTiufBcE0BFX0cJ5roUtVoY6r8TKUTJ1u4RUZLZHYsXqjR8/s1600/Right+Time+Image.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="160" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEibHtKyjH3YxHlpJiaN3EJ7sAWT4aZuUbhfKYcggXhCnAwl8OJp3FTq7BJaflyUbNEfkWgL17JZQS_visRnyfzPlljea9-9KTiufBcE0BFX0cJ5roUtVoY6r8TKUTJ1u4RUZLZHYsXqjR8/s200/Right+Time+Image.jpg" width="200" /></a><strong><span style="color: red; font-size: large;">What is (NOT) the Right Time for Pushing Promotional Messages</span></strong><br />
<br />
We have already had a look at the methods to identify the right time from<a href="http://analyticsdud.blogspot.in/2013/02/segmentation-standards-framework.html" target="_blank"> customer segmentation</a> or from <a href="http://analyticsdud.blogspot.in/2012/12/what-are-steps-in-nbo-next-best-offer.html" target="_blank">propensity models</a><br />
<br />
However, the real-time delivery of messages is a key in today's world. The customer might be in a different location or might be scanning for important news in his Facebook.<br />
<br />
For example, pushing a promotional message during Boston Marathon is an example for NOT pushing promotions.<br />
<br />
<strong><span style="color: red;">Business Rules and Next Best Action</span></strong><br />
<br />
The above example is a good one for using a Rules Engine to filter / time the delivery of the messages. There are open source Rules engine like <a href="http://www.jboss.org/drools/" target="_blank">Drools</a> that can be used to create and maintain business rules .<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-43769430344708630922013-04-23T04:44:00.000-07:002013-04-23T04:44:32.476-07:00How to use OLAP for interpreting Cluster Results<br />
<strong><span style="color: orange; font-size: large;">How to Intepret Clustering Results / K-means Cluster output using Data Warehouse</span></strong><br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj40N9HoYQQj0Og46hzLJGWVwbfQDo2INBVWmQNL5pe1DdnfQrHFPOiFKH1N0c1JeagIBjJNih5R3P8LJ-AkCC18EsN_ifnZV4oTlq_aXmnLNkwZSCnrs3YX-wtYFGDYuWIai9_toIa1Sk/s1600/All+About+Analytics+-+How+to+use+OLAP+Cubes+for+K-Clustering.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj40N9HoYQQj0Og46hzLJGWVwbfQDo2INBVWmQNL5pe1DdnfQrHFPOiFKH1N0c1JeagIBjJNih5R3P8LJ-AkCC18EsN_ifnZV4oTlq_aXmnLNkwZSCnrs3YX-wtYFGDYuWIai9_toIa1Sk/s320/All+About+Analytics+-+How+to+use+OLAP+Cubes+for+K-Clustering.png" width="320" /></a></div>
OLAP and Clustering ? Strange combination isn't it? OLAP - we know what to do, what fields to aggregate, slice and dice, what report to show and what fields to show. Clustering on the other hand is looking for groups (with or without a particular goal ). How OLAP can then help Clustering. Please Read on. You might be convinced to try<br />
<br />
K-means (or any other method) clustering partitions the data into groups that are homogeneous with respected to the cluster variables. <br />
<br />
The output mostly would be the primary variable, and its associated cluster along with other cluster / segmentation variables<br />
<br />
<strong>Cluster Profiling / Interpretation</strong><br />
<br />
Though cluster output and their scatter plot provides some interesting findings, it's the cluster profiling that helps the user in a better way<br />
<br />
<strong>OLAP and Data Warehousing</strong><br />
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiMK1mqDhxmL4pGtGHXRmttqeXHKPEPvSY7ff6yfdfgqVLOl-AGCnHNQF0W5QcJeeeUGpoabu-x2DXrbWl2wcQdRu1Nmo-q87iIylMYcz1KnKll-0vkcxcGU5wDOMaAfuMmosmpJbepBss/s1600/All+About+Analytics+-+How+to+use+OLAP+Cubes+for+Clustering.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="237" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiMK1mqDhxmL4pGtGHXRmttqeXHKPEPvSY7ff6yfdfgqVLOl-AGCnHNQF0W5QcJeeeUGpoabu-x2DXrbWl2wcQdRu1Nmo-q87iIylMYcz1KnKll-0vkcxcGU5wDOMaAfuMmosmpJbepBss/s320/All+About+Analytics+-+How+to+use+OLAP+Cubes+for+Clustering.png" width="320" /></a>OLAP is an BI (Business Intelligence) approach to answering multi-dimensional analytical queries in real or near-real time</div>
<br />
OLAP consists of Facts, Fact Tables, Dimension tables, Cubes that contains the precise data for a given requirement etc. <br />
<br />
<strong>OLAP and Clustering</strong><br />
<br />
If the cluster output along with the interpretation variables and the cluster score (index) is fed to the OLAP and analyzed, it will provide a faster way of Cluster Interpretation and through many interesting insights<br />
<br />
In similar way decision tree results can also be fed back to OLAP (<a class="g-profile" href="http://plus.google.com/115607918987921226255" target="_blank">+Oracle</a> , <a class="g-profile" href="http://plus.google.com/102687218278688747710" target="_blank">+SQL Server</a> , <a class="g-profile" href="http://plus.google.com/115541610744191708285" target="_blank">+Terradata AG</a> )<br />
<br />
Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-34303199315050869452013-04-17T22:31:00.000-07:002013-10-04T21:50:18.712-07:00How to Segment Social Media Users (Influencers / Detractors / Recommenders)<strong><span style="color: orange; font-size: large;">Segmentation of Social Media Influencers</span></strong><br />
<br />
We have seen in the past about the <a href="http://analyticsdud.blogspot.in/2013/02/segmentation-standards-framework.html" target="_blank">Retail Specific Segmentation Standards</a> and also some <a href="http://analyticsdud.blogspot.in/2013/04/widely-used-segmentation-products.html" target="_blank">Segmentation Tools</a> that help to achieve that.<br />
<br />
Here we would delve bit deep into segmenting the social media users. <br />
<br />
<strong><span style="color: red;">Behavioral Segmentation of Social Media Users</span></strong><br />
<br />
Social media users are classified as shown by the <a href="http://klout.com/corp/klout_score" target="_blank">Klout</a> Influencer Matrix given below<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgzPtrmAIjX2Joxsy2ydsALA4OkthZUh5GssZeqQ8rr8nyFcfK1ifOp9hntC8KZTvoT4mfoEsTzVCKmb7r1Cn7FJ9PBj_UJgRNOfoeqXcIQPsHBisOe1ZNZSQpAp2JuKyf3B2Oa53O7QkU/s1600/Social+Media+Influencer+Matrix+from+Klout.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" height="640" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgzPtrmAIjX2Joxsy2ydsALA4OkthZUh5GssZeqQ8rr8nyFcfK1ifOp9hntC8KZTvoT4mfoEsTzVCKmb7r1Cn7FJ9PBj_UJgRNOfoeqXcIQPsHBisOe1ZNZSQpAp2JuKyf3B2Oa53O7QkU/s640/Social+Media+Influencer+Matrix+from+Klout.jpg" width="600" /></a></div>
<br />
<br />
Depending on the Need / Goal, one can select the specific segment of users. <a href="http://www-01.ibm.com/software/analytics/spss/" target="_blank">IBM's Social Analytics Tool (SPSS)</a> helps to identify the following from Social Data<br />
<br />
<ul>
<li>Influencers</li>
<li>Recommenders</li>
<li>Detractors</li>
</ul>
The above combined with customer and transaction data would give necessary insights into customer behavior<br />
<br />
<strong><span style="color: red;">Merging Social Data with CRM / Customer Data</span></strong><br />
<br />
The social users can also be segmented by demographics, geographics, which would provide information that might not be captured in CRM (for example, <a class="g-profile" href="http://plus.google.com/115684033096930245910" target="_blank">+Microsoft Dynamics ERP</a> )<br />
<br />
<b><span style="color: red;">The 7 elements of social data</span></b><br />
<br />
<a href="http://sanzasurf.tumblr.com/" target="_blank">Sandile Mayambala</a> a digital analyst as come up with the following combinations<br />
<br />
<ul>
<li>demographic</li>
<li>product</li>
<li>psychographic</li>
<li>behavioral</li>
<li>referrals</li>
<li>location</li>
<li>intention</li>
</ul>
<br />
It may not be possible to get all data points for every customer. In that case the data is normalized and analyzed<br />
<br />
See also :<a href="http://analyticsdud.blogspot.in/2013/03/how-to-find-social-influencers-using.html"><span style="color: #cc6611;">How to Find Social Influencers using analytics</span></a>, <br />
<span style="font-size: small;"><a href="http://socialmediatoday.com/node/448280" target="_blank">Five Types of Social Media Influencers</a></span>Unknownnoreply@blogger.com3tag:blogger.com,1999:blog-1872026853745700770.post-18549758575969195812013-04-17T06:17:00.000-07:002013-04-17T06:17:09.852-07:00Link-Selling Analytics (Web Analytics)<strong><span style="color: red; font-size: large;">How does Analytics help efficient Link-Selling</span></strong><br />
<br />
<strong>Link-Selling</strong> is a form of cross-selling , <br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiCdKonhyMyMRPh9TYMZpLQ4jLDKneKSaDq8rJglk2oK5IATJFVdO12aer9Vsxfdi7FhkLeoV_G8DMzRxB2HVSMYqCMk_0rc2C_0wNdkuLh6kpBNEO9xPVQKa-BklSSFdmaYyexeHQopy0/s1600/Cross+Sell.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="127" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiCdKonhyMyMRPh9TYMZpLQ4jLDKneKSaDq8rJglk2oK5IATJFVdO12aer9Vsxfdi7FhkLeoV_G8DMzRxB2HVSMYqCMk_0rc2C_0wNdkuLh6kpBNEO9xPVQKa-BklSSFdmaYyexeHQopy0/s200/Cross+Sell.jpg" width="200" /></a>
which occurs when a product is selected. Then the shopper taken through a series of ‘yes/no’ questions regarding ‘additional extras’ that can be added to the cart. <br />
<br />
The catch here is there would be series of questions put up and the the subsequent questions should be modified/updated according to the previous one.<br />
<br />
Though mostly the logic is rule-based, use of Predictive modeling increases accuracyUnknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-88600915905915415172013-04-17T02:17:00.000-07:002013-04-17T02:17:27.534-07:00Customer Analytics - Understand Mood of the Day<strong>How to Analyze Customer Behavioral Changes on Time (Day)</strong><br />
<br />
<br />
<br />
<a href="http://1.bp.blogspot.com/cjOAJOM5hfTKeTIqtpon6hv8jgN2B1BWsZFa5gC800_ihUcoY_fGtg7S64tV-SER0vA=w705" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"></a><br />
<a href="http://1.bp.blogspot.com/cjOAJOM5hfTKeTIqtpon6hv8jgN2B1BWsZFa5gC800_ihUcoY_fGtg7S64tV-SER0vA=w705" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><a href="http://www.netflix.com/" target="_blank"><img border="0" height="97" src="http://1.bp.blogspot.com/cjOAJOM5hfTKeTIqtpon6hv8jgN2B1BWsZFa5gC800_ihUcoY_fGtg7S64tV-SER0vA=w705" width="200" /><br />
<br />
</a><a href="http://www.netflix.com/" target="_blank">Netflix</a> - the world's leading Internet television network with more than 33 million members in 40 countries has developed an algorithm (Cinematch recommender tool) that can predict the movies that a customer would watch based on </a><br />
<br />
<ul>
<li>Past behavior (view history)</li>
<li>Product rating</li>
<li>Recent comparison</li>
</ul>
<br />
Cinematch uses Nearest Neighbor method for predicting a movie<br />
<a href="http://www.phonejunkie.org/wp-content/uploads/2013/03/ATT-29542_logo.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="http://www.phonejunkie.org/wp-content/uploads/2013/03/ATT-29542_logo.jpg" width="200" /></a><br />
The company decided to have an Open contest to fine tune the recommendations (or the <a href="http://analyticsdud.blogspot.in/2012/12/what-are-steps-in-nbo-next-best-offer.html" target="_blank">Next Best Action</a> if you wanted it to be called so) - the winner would be the one who beat the recommendation of Cinematch by 10%.<br />
<br />
AT&T with the combination of nearest neighbor , singular value decomposition (SVD) methods were able to win the one <br />
<br />
<br />
Please have a look at <a href="http://www.research.att.com/articles/featured_stories/2010_01/2010_02_netflix_article.html?fbid=8rnpOtsYzRv">http://www.research.att.com/articles/featured_stories/2010_01/2010_02_netflix_article.html?fbid=8rnpOtsYzRv</a> for the full text.<br />
<br />
<br />
<br />
<br />
<br />Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-38513007815628772132013-04-14T22:30:00.002-07:002013-08-11T07:04:04.462-07:00Widely used Segmentation Products / Solutions<strong><span style="color: red; font-size: large;">Free Segmentation Frameworks / Products</span></strong><br />
<br />
We had an indepth analysis of various segmentation frameworks for profiling customers in <a href="http://analyticsdud.blogspot.in/2013/02/segmentation-standards-framework.html"><span style="color: #cc6611;">Segmentation Standards / Framework</span></a>. Here we will look in more detail on some readily available Segmentation products that will accelerate segmentation/clustering.<br />
<br />
<br />
<br />
Prizm's market segmentation comes-up with beautiful segments for a particular Zipcode. If you want to open a Store in the locality <strong>ZIP Code 65231, Auxvasse, MO</strong>. Here are the results from the search (<a href="http://www.claritas.com/MyBestSegments/Default.jsp?ID=20">http://www.claritas.com/MyBestSegments/Default.jsp?ID=20</a>#)<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEikTauZBnaAUdjWms7r2GQEjOx8UpSSzrNE0JSQIOuZZWrT9ZwCM1l2tlff4mWFA0j47QucVsfU8WEkfz_02bMdZinNOa3SSOw5AHH0WHwUllly9MxoxS3WVoaH9S5D5hEOsfKvLQ3w8NU/s1600/Claritas+Segmentation+Prizm+Framework+Customer+Loyalty+analytics.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" height="336" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEikTauZBnaAUdjWms7r2GQEjOx8UpSSzrNE0JSQIOuZZWrT9ZwCM1l2tlff4mWFA0j47QucVsfU8WEkfz_02bMdZinNOa3SSOw5AHH0WHwUllly9MxoxS3WVoaH9S5D5hEOsfKvLQ3w8NU/s640/Claritas+Segmentation+Prizm+Framework+Customer+Loyalty+analytics.png" width="640" /></a></div>
<br />
<br />
<br />
<a href="http://media.marketwire.com/attachments/200812/TN-493436_PersonicxWheel_forPrint.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" height="188" src="http://media.marketwire.com/attachments/200812/TN-493436_PersonicxWheel_forPrint.jpg" width="200" /></a><a href="http://www.intelligenttargeting.com/analytics/personicx" target="_blank">PersonicX</a> is a household-level segmentation system including 70 clusters
and 21 life stages. The PersonicX suite helps to know and
anticipate customers’ demographics and buying behaviors, conduct
market analysis, plan customer acquisition strategies, and create
cross-sell, up-sell and retention campaigns that are truly targeted,
personalized and powerful.<br />
<br />
<br />
<br />
<br />
<br />
<a href="http://images.all-free-download.com/images/graphiclarge/forrester_65080.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="http://images.all-free-download.com/images/graphiclarge/forrester_65080.jpg" width="200" /></a><a href="http://empowered.forrester.com/tool_consumer.html" target="_blank">Forrester's Social Technographics data</a> classifies consumers into <a href="http://empowered.forrester.com/ladder2010">seven overlapping levels of social technology participation</a>.
Based on their proprietary Consumer Technographics survey data, they can <br />
share with how social participation varies among your consumers
globally and help plan a targeted social technology strategy. <br />
<br />
<iframe frameborder="0" height="360" marginheight="0" marginwidth="0" scrolling="no" src="http://empowered.forrester.com/groundswell/b2c_profile_tool/b2c" width="510"> </iframe><br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiez6871-Di309hOMzDMOm6C7J2IFlrHjRVOAlwrNLfox6LkDQDdF2XjDcejoOPBocL8ofPmyLUDF0-Y7r3hA77IFCjag85qdvYDz9l3P_pJzPgp0BZUuHOe8AHVHiXuvHPfadgnnmrkEg/s1600/Montetate+Logo.png" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" height="71" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiez6871-Di309hOMzDMOm6C7J2IFlrHjRVOAlwrNLfox6LkDQDdF2XjDcejoOPBocL8ofPmyLUDF0-Y7r3hA77IFCjag85qdvYDz9l3P_pJzPgp0BZUuHOe8AHVHiXuvHPfadgnnmrkEg/s320/Montetate+Logo.png" width="320" /></a></div>
<a class="g-profile" href="http://plus.google.com/115539195687110933777" target="_blank">+Monetate</a>'s LivePredict is an automated segment discovery product that automatically identifies valuable customer segments and the attributes that define them. This gives marketers the ability to<br />
instantly take action by targeting offers and content specifically to those segments
<br />
<br />
<a class="g-profile" href="http://plus.google.com/104091350754522171148" target="_blank">+OfficeMax</a> is using LivePredict to identify highest and lowest performing segments at both brand and campaign levels
Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-74383044584165094862013-04-12T23:45:00.003-07:002013-04-12T23:46:46.650-07:00Creating Valuable Data Columns - Aggregate Data<span style="font-size: large;"><span style="color: orange;"><b>How to create insightful summary data from Operational Data</b></span></span><br />
<br />
Analytics is not a magic wand. It produces useful insights when fed with good data, insightful information. The primary source of information is from Operational Data.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/proxy/AVvXsEjGZxKxqP7GxY8BRUWmgr5cRf1q77i-FkjhJ8vSSVYQ4k1BSr2ihyubYnjiirdgVzTPNHbHLZdECwZO3WWcIV5neJM2NSo7ftmUVOxlGZW130U0HBOuirQ3ntp4OjDko6A2mXBnDCP9sd7h_Z3MG3O4lNAsu9ZSpcxHszT1ig4=" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/proxy/AVvXsEjGZxKxqP7GxY8BRUWmgr5cRf1q77i-FkjhJ8vSSVYQ4k1BSr2ihyubYnjiirdgVzTPNHbHLZdECwZO3WWcIV5neJM2NSo7ftmUVOxlGZW130U0HBOuirQ3ntp4OjDko6A2mXBnDCP9sd7h_Z3MG3O4lNAsu9ZSpcxHszT1ig4=" /></a></div>
<br />
<br />
The operational data, however, is not quite useful as it is . It needs to be rolled-up to form a good amount of data points.<br />
<br />
Some days back we were looking at the importance of <a href="http://analyticsdud.blogspot.in/2013/04/customer-analytics-relative-price-as.html" target="_blank">Relative Pricing in Customer Analytics</a>. Another real world example would be the Bizocity scores used by <a href="http://www.att.com/" target="_blank">AT&T</a><br />
<br />
Bizocity score takes into account the originating call number, the destination, the duration etc to arrive at the score.<br />
<br />
See also: <a href="http://analyticsdud.blogspot.in/2013/03/case-study-customer-analytics-for.html">Case Study: Customer Analytics for Telecom Operator to Cross-Sell and Up-Sell</a>
<!-- Blogger automated replacement: "http://images-onepick-opensocial.googleusercontent.com/gadgets/proxy?container=onepick&gadget=a&rewriteMime=image%2F*&url=http%3A%2F%2Fwatchdognation.com%2Fwp-content%2Fuploads%2F2013%2F01%2Fatt-1.jpg" with "https://blogger.googleusercontent.com/img/proxy/AVvXsEjGZxKxqP7GxY8BRUWmgr5cRf1q77i-FkjhJ8vSSVYQ4k1BSr2ihyubYnjiirdgVzTPNHbHLZdECwZO3WWcIV5neJM2NSo7ftmUVOxlGZW130U0HBOuirQ3ntp4OjDko6A2mXBnDCP9sd7h_Z3MG3O4lNAsu9ZSpcxHszT1ig4=" -->Unknownnoreply@blogger.com0tag:blogger.com,1999:blog-1872026853745700770.post-28239295894279967782013-04-02T00:18:00.001-07:002013-11-02T08:02:59.671-07:00Customer Analytics - Relative Price as Data Point<strong><span style="color: orange; font-size: large;">Relative Pricing in Customer Behaviour Analytics </span></strong><br />
<br />
We had some discussion on <a href="http://analyticsdud.blogspot.in/2012/12/how-to-measure-price-sensitity-of.html">Price Sensitivity earlier</a>. This was used for determining the Right Price of offer for that customer. However, the price sensitivity is more related to Demand Elasticity <br />
<div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="http://farm3.staticflickr.com/2707/4157275061_5f0a909cae.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" height="212" src="http://farm3.staticflickr.com/2707/4157275061_5f0a909cae.jpg" width="320" /></a></div>
</div>
<strong>Relative Price</strong> is the price of a product/service with respect to another product/service. The latter one is usually termed as the base product/service.<br />
<br />
<strong><span style="color: red;">How to use Relative Price to understand Customer Behaviour</span></strong><br />
<br />
<a href="http://www.freestufffinder.co.uk/wp-content/uploads/2012/08/free-tea-twinings.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="http://www.freestufffinder.co.uk/wp-content/uploads/2012/08/free-tea-twinings.jpg" width="197" /></a>Relative price provides very much useful insight about the customer's behaviour. The following would be the typical values for Relative price<br />
<br />
<ul>
<li>High</li>
<li>Medium</li>
<li>Low</li>
</ul>
The relative price is applied to each item based on a base item from that category. For example a segregating a customer based on the<br />
<a href="http://www.packagingeurope.com/images/news/230710_101525_tetley.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="141" src="http://www.packagingeurope.com/images/news/230710_101525_tetley.jpg" width="200" /></a> different price preferences (Twinnings Tea might be a High valued one, while Tetley might be Medium priced; depending on the purchase behavior of each individual across category the following Relative Pricing Table is created)<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgGVFtFBz37QCKnIQwyL-Yv6U2qQEZ1Oldivm4bM8bS0YFFdqhyphenhyphen16QacM4AvKLYElHnGDclQYNxiQymTO9mCPqOE10wwJxO1LFblLSeYkpwHEsJFfO-IA-mjm6c_ffJYFvD8GffbnXAvRLt/s1600/redrose.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="151" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgGVFtFBz37QCKnIQwyL-Yv6U2qQEZ1Oldivm4bM8bS0YFFdqhyphenhyphen16QacM4AvKLYElHnGDclQYNxiQymTO9mCPqOE10wwJxO1LFblLSeYkpwHEsJFfO-IA-mjm6c_ffJYFvD8GffbnXAvRLt/s200/redrose.jpg" width="200" /></a></div>
<table border="0" cellpadding="0" cellspacing="0" style="border-collapse: collapse; width: 424px;">
<colgroup><col style="mso-width-alt: 2929; mso-width-source: userset; width: 62pt;" width="82"></col>
<col style="mso-width-alt: 2986; mso-width-source: userset; width: 63pt;" width="84"></col>
<col style="mso-width-alt: 2161; mso-width-source: userset; width: 46pt;" width="61"></col>
<col style="width: 48pt;" width="64"></col>
<col style="mso-width-alt: 2446; mso-width-source: userset; width: 52pt;" width="69"></col>
<col style="width: 48pt;" width="64"></col>
</colgroup><tbody>
<tr height="19" style="height: 14.4pt;">
<td class="xl63" height="19" style="background: rgb(155, 187, 89); border: 0.5pt solid windowtext; color: white; font-family: Calibri; font-size: 11pt; font-weight: 700; height: 14.4pt; mso-pattern: #9BBB59 none; text-decoration: none; text-line-through: none; text-underline-style: none; width: 62pt;" width="82">Cust ID</td>
<td class="xl64" style="background: rgb(155, 187, 89); border: 0.5pt solid windowtext; color: white; font-family: Calibri; font-size: 11pt; font-weight: 700; mso-pattern: #9BBB59 none; text-decoration: none; text-line-through: none; text-underline-style: none; width: 63pt;" width="84">Category</td>
<td class="xl64" style="background: rgb(155, 187, 89); border: 0.5pt solid windowtext; color: white; font-family: Calibri; font-size: 11pt; font-weight: 700; mso-pattern: #9BBB59 none; text-decoration: none; text-line-through: none; text-underline-style: none; width: 46pt;" width="61">Premium</td>
<td class="xl64" style="background: rgb(155, 187, 89); border: 0.5pt solid windowtext; color: white; font-family: Calibri; font-size: 11pt; font-weight: 700; mso-pattern: #9BBB59 none; text-decoration: none; text-line-through: none; text-underline-style: none; width: 48pt;" width="64">High</td>
<td class="xl64" style="background: rgb(155, 187, 89); border: 0.5pt solid windowtext; color: white; font-family: Calibri; font-size: 11pt; font-weight: 700; mso-pattern: #9BBB59 none; text-decoration: none; text-line-through: none; text-underline-style: none; width: 52pt;" width="69">Medium</td>
<td class="xl65" style="background: rgb(155, 187, 89); border: 0.5pt solid windowtext; color: white; font-family: Calibri; font-size: 11pt; font-weight: 700; mso-pattern: #9BBB59 none; text-decoration: none; text-line-through: none; text-underline-style: none; width: 48pt;" width="64">Low</td>
</tr>
<tr height="19" style="height: 14.4pt;">
<td class="xl66" height="19" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; height: 14.4pt; text-decoration: none; text-line-through: none; text-underline-style: none;">RF0000123</td>
<td class="xl67" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">OVGT120980</td>
<td class="xl68" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">0</td>
<td class="xl68" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">6</td>
<td class="xl68" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">16</td>
<td class="xl69" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">0</td>
</tr>
<tr height="19" style="height: 14.4pt;">
<td class="xl70" height="19" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; height: 14.4pt; text-decoration: none; text-line-through: none; text-underline-style: none;">RF0000227</td>
<td class="xl71" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">OVGT120980</td>
<td class="xl72" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">11</td>
<td class="xl72" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">3</td>
<td class="xl72" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">2</td>
<td class="xl73" style="background-color: transparent; border: 0.5pt solid windowtext; color: black; font-family: Calibri; font-size: 11pt; font-weight: 400; text-decoration: none; text-line-through: none; text-underline-style: none;">0</td>
</tr>
</tbody></table>
<div style="text-align: center;">
<strong>Relative Pricing Customer Table</strong></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
)Looking at the above table, one could distinguish between the customers - (for a particular category) - the second customer mostly shops for Premium items, while the former is a bit conservative.<br />
<br />
The above methodology can be used and the following can be used as Segmentation variables <br />
<br />
<ul>
<li>No of High Value Items</li>
<li>No of Medium Value items</li>
<li>No of Low Value items</li>
</ul>
<br />
Please try this out and let us know the difference it brought to your segments<br />
<br />
<b><span style="color: #990000; font-size: large;">How to measure effectiveness of Switcher Campaigns in Retail </span></b><br />
<br />
Switcher campaigns are the one that disrupt brand loyalty and tease an otherwise loyal customer to switch over to the competitor. Tetley and Brooke Bond are competitors - what would be the impact of providing an offer on Brooke Bond tea for a Tetley fan.<br />
<br />
<a href="http://www.dunnhumby.com/" target="_blank">dunnhumby's </a>analysis on offers finds Switcher campaigns are always the worst performing. According to the reporthouseholds tend to buy more of their favorites, such as Coke products, or a new Coke product, if offered an incentive rather moving to Pepsi for example
<br />
<br />
<br />Unknownnoreply@blogger.com1tag:blogger.com,1999:blog-1872026853745700770.post-18945310746827561052013-03-30T19:56:00.000-07:002013-09-01T00:48:07.038-07:00Case Study: Customer Analytics for Telecom Operator to Cross-Sell and Up-Sell<strong><span style="color: red; font-size: large;">How to find products/services to Cross-Sell / Up-Sell using Customer analytics / NBO</span></strong><br />
<br />
The Telecom operator has a good customer base and wants to drive more sales using existing customers. The operator decided to craft a <a href="http://analyticsdud.blogspot.in/2012/12/what-are-steps-in-nbo-next-best-offer.html">NBO strategy</a> for increasing sales from existing customers (this is not just retaining the customer - by reducing Churn)<br />
<br />
<a href="http://getentrepreneurial.com/wp-content/uploads/2012/06/increase-sales.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="199" src="http://getentrepreneurial.com/wp-content/uploads/2012/06/increase-sales.jpg" width="200" /></a>As with any NBO - the first step is to determine the Objective <br />
<br />
<strong>Step 1: Define The Objective</strong><br />
<br />
The objective here is - Increase sales from existing customer through cross-sell or up-sell<br />
<br />
A customer with two or more services is four times less likely to Churn than a customer with a singl service - this means that <span style="color: blue;">cross-sell not only increases the incremental sales but also increases Loyalty</span>. The strategic objectives like these should be driving the NBO objective<br />
<br />
With the goal being defined very clearly, the next step is to collect required data for the NBO<br />
<br />
<strong>Step 2: Collect Data </strong><br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhv7UzdSaNg7C4p7KU-qlIwd_cN-PBoWfitwBvMLrEmTyy5inxdEQGbJknFZRzpQwqahkNpNeIEnBXt7QiYUPvYc68XaIZsp51geZR0_kT7iuhkCi31SH1APoadvrPT2LYC1QOjt9s9L7Q/s1600/database.png" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhv7UzdSaNg7C4p7KU-qlIwd_cN-PBoWfitwBvMLrEmTyy5inxdEQGbJknFZRzpQwqahkNpNeIEnBXt7QiYUPvYc68XaIZsp51geZR0_kT7iuhkCi31SH1APoadvrPT2LYC1QOjt9s9L7Q/s200/database.png" width="200" /></a></div>
The Telecom operator has data on the services/products that are used by each customer, the plan, the usage history, subscription data, the CDRs , Customer Demographics data and Internet usage data (for the subscribers) . This data holds wealth of information and needs to be mined.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
The entry channel (the channel through which the customer was acquired) would be a vital information. <br />
<br />
The Location data also plays an important role in understanding the customer, Location history would explain if the customer is a frequent traveller, when and where he/she makes uses the service.<br />
<br />
If the internal data collection is done, one can look for Syndicate data or External Data (<a href="http://analyticsdud.blogspot.in/2013/03/payment-card-industry-crucial-for-real.html">Payment Card data</a>)<br />
<br />
<strong>Step 3: Analyze, Model and Execute</strong><br />
<br />
Once the Data is available, it needs to be cleaned and normalized. Then the customers are segmented based on their purchase behavior, subscription plans etc. There are also industry specific segmentation standards like <a href="http://analyticsdud.blogspot.in/2013/02/segmentation-standards-framework.html">Prizm</a>. This should be a good input for rolling up data<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="http://www.window2win.com/ayancherinews/sp_images/bsnl-mobile_lady.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" height="198" src="http://www.window2win.com/ayancherinews/sp_images/bsnl-mobile_lady.jpg" width="200" /></a></div>
<strong>Understanding the customer</strong> is a first stage in NBO. The customer's behavioral attributes are <br />
analyzed using statistical analysis (clustering, link analysis, decision trees), predictive modelling etc. <br />
<br />
It's just not about understanding the customer, the Telecom company needs to analyze the product/service that can be offered to a particular segment. <strong>Understanding the Service/Product Offering</strong> is the next stage . <br />
<br />
For example, <br />
<ul>
<li>Wireless devices</li>
<li>WiFi Services</li>
<li>VOIP Call services</li>
<li>Local call services</li>
<li>Broadband Direct connection</li>
<li>loud hosting</li>
</ul>
<br />
For example, a propensity model can be created for knowing the probability of the customer for purchasing/trying a particular product / service. For example, a Broadband plan for a customer who is not using the services from the operator (and using the one from a Competitor) with competitive pricing / value add would entice the customer to switch-over.<br />
<br />
The propensity of a customer who is currently using the service is set to Zero. This will avoid irittating the customer with the product/service she already uses.<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="http://www.prlog.org/12068599-amazon-coupon-codes-february-2013-and-amazon-promo-codes-february-2013.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" height="151" src="http://www.prlog.org/12068599-amazon-coupon-codes-february-2013-and-amazon-promo-codes-february-2013.jpg" width="200" /></a></div>
<br />
The propensity of each service is ranked along with the best suited time of sending the offer. The Offer is then sent to the customer through his prefered Channel and at the <strong>appropriate context</strong>.<br />
<br />
Context is always the key - if someone has a 4G-enabled phone, he has a fair chance of upgrading to a 4G network. Knowing the user's device information is helpful here.<br />
<br />
<br />
<br />
Tools like <a href="http://www.sas.com/">SAS</a> and <a href="http://www.ibm.com/software/analytics/spss/" target="_blank">SPSS</a> can help in achieving this faster. There are <a href="http://analyticsdud.blogspot.in/2012/11/open-source-software-for-analytics.html" target="_blank">Open Source Software - like R</a>, which is catching up fast<br />
<br />
<strong>Step 4: Measure and Recalibrate</strong><br />
<br />
<span style="color: red;">Every offer that is sent is an Test Offer</span>. An offer can be accepted/ignored/rejected. The best NBO strategy is to measure the response of the offer and take the learning back to Analysis stage.<br />
<br />
The offer response data is fed back to the database. If there is any need for further data points, it needs to be collected. The model is then refreshed based on the new analysis and deployed.<br />
<br />
<table align="center" cellpadding="0" cellspacing="0" class="tr-caption-container" style="margin-left: auto; margin-right: auto; text-align: center;"><tbody>
<tr><td style="text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5PwPD8ie4uVtYtj2YNmZw8KqrrEYM0_asEbtHR0HDEaYYvKC5P1pyosPkykMkhiDqolaXC4FXUQoJUTsQAzS7Q6D40x2WXhXKP8mAhNY8QfHSQQCgpLWfExTzYjQebIBPZbMKQTZCu4E/s1600/Next+Best+Offer+-+Framework.png" imageanchor="1" style="margin-left: auto; margin-right: auto;"><img border="0" height="480" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5PwPD8ie4uVtYtj2YNmZw8KqrrEYM0_asEbtHR0HDEaYYvKC5P1pyosPkykMkhiDqolaXC4FXUQoJUTsQAzS7Q6D40x2WXhXKP8mAhNY8QfHSQQCgpLWfExTzYjQebIBPZbMKQTZCu4E/s640/Next+Best+Offer+-+Framework.png" width="640" /></a></td></tr>
<tr><td class="tr-caption" style="text-align: center;">Next Best Offer Solution Framework</td></tr>
</tbody></table>
<br />
This is a continous cycle and the role of Statisticans, Business Leaders play an important role<br />
<br />
<br />
<br />Unknownnoreply@blogger.com2