Advanced Analytics in Learning / Education / Writing / Research

How will Analytics help Education in Schools and Colleges

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. 


Declara is an intelligent social learning platform - Fo+Ramona Pierson and +Nelson Gonzalez 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. As people learn, Declara learns!  

How to Predict a Best Seller (Book) Algorithmically

Analytics can help the publisher identify a best seller from the language and style of the writing (from the manuscripts)


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 statistical stylometry, a statistical analysis of literary styles in several genres of books and identified characteristic stylistic elements more common in successful tomes than unsuccessful ones.

Sentiment Analysis To Determine bias in Articles / Publications of an Author

Its seldom possible to be neutral as a journalist. We all have some bias for / against someone / something or some corporation. +Rami Nuseir in his article on Strange uses of Sentimental Analysis explains the use of technique to identify the bias of an author based on previous articles. A plugin created using +Semantria analyses previous works of an author and scores the same based on their neutrality. This prediction helps the reader to identify the correct material

Supply Chain Analytics in Retail World

How Supply Chain Analytics is improving the efficiency in Retail World

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

Supply chain analytics helps the retailer understand and predict it much before

Ticketing Supply Lead Time - Urban Outfitters

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.

FastTrak Analytics is an internet-based software package for order processing, tracking and management of the ticketing function developed by +Fineline Technologies

The new analytical reporting tool will provide Urban Outfitters and FineLine’s base of 200 brand name retail customers with three core reports:

order turnaround time, which calculates the average time between receipt of an order by FineLine and shipment of tickets;
order received time, as the average time between receipt of an order by FineLine and delivery of tickets to vendors;
orders shipped to country, as the average time between receipt of an order by FineLine and delivery of tickets to vendors in a specific country.

Next Best Action and A/B Testing

How to use A/B Testing for Customer Analytics

Next Best Action is a learning based on the response of the previous action. Every action/offer is an test offer.

A/B split testing

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

Mail Open
Clicks on Links
Conversion (Purchase etc)

If say the more number of Message As are clicked than Message B, then A is said to be more effective.

Email Response analysis

The responses are then analysed - responders / non-responders are segmented and analysed. The model is then refreshed.

Once the model is refreshed the customers can be retargeted / left alone

Retargeting Customers

Retargeting is to try out the offer / promotion / message another time. They can send the same message / a different customized message


A/B Testing in Web Page Design / Website Traffic

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


Case Study - Victoria Secret A/B Testing

Victoria Secret - the leading eCommerce vendor is testing its

Email Subject lines
Offer and Image











using A/B testing (see Site Doublers for the complete case study)

Web Analytics - Repeat Customers

+Adobe  report shows that repeat customers who are 8% of the ecommerce traffic contribute 41% of the sales.

Sale by 1 Repeat Customer = 11 times x Sale by New Customer

+Econsultancy shows that the sales of the customers increased by the repeat of the visits

Sales by Second Time Customer = 3 times x Sale by First Customer

Going by all these metrics its imperative that repeat customers are a Golden Goose. How to keep the customers / make the customers buy again?

Connecting with Customers

Retailers (Online/Offline) need to have constant touch with the customers. They would need to send relevant offers/messages (what is called as Next Best Action today) at right time through right channel
+Yebhi India 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

A good marketing should take care of the Context and the customer's purchasing power/ intention into account before sending him/her the message

Companies like +Store Express etc provide ecommerce consultancy in this area.  +IBM's
Digital Analytics has powerful analytics tools that can help to create, measure and monitor key metrics

One of the primary channel nowadays is Mobile Anna's Linens is 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

Location Based Predictive Analysis using Crowd/Social Data - Traffic Congestion Analytics / Parking Space Analytics

How to use Social/Location data for Big Data Analytics / Real-Time analytics


The real use of Analytics is slowly emerging. This time let's review some Mobile Apps build using +Android, Apple and +Windows Phone

Parko - 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


+Waze - that was recently acquired by +Google, Inc. uses real-time information from nearby drivers to find the best path. It is basically a GPS-based navigational app which uses turn-by-turn navigation and the historical user-submitted travel times and route details

The +Traveling Salesman algorithm can be tested here.

Real-time analytics need Big Data infrastructure where companies like +Cloudera and +Hortonworks play a key part. With Internet of Things gaining popularity the Apps will be replaced by the Cars itself. Some models from +Ford Motors  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.

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.

Location based analytics also involves predicting the behaviour of the user based on his/her current navigation.

Geo Fencing in Marketing

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

• Delimiting Geofencing Perimeter
• Analyze Perimeter Segments
• Data Integration (Location with Transactional and Customer data)
• Location sensitive content / message / offer creation
• Privacy Filtering
• Location based Delivery

Customer analytics from Anonymous In-Store Customers (In-Store Shopper Analytics)

How to Perform Data Analysis on Anonymous Customers who have Purchased In-Store with Cash

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 (Payment Card Industry - Crucial for Real-Time Next Best Action (NBA) - Big Data)


How to Track Anonymous Customers

Tracking Anonymous customers (visitors) on the web is quite easy nowadays. The Cookies, IP
Addresses etc provide a wealth of information and this can be used when the visitors return. Tools like SAS, SPSS, +IBM Smarter Analytics and Manthan Systems's ARC Customer Analytics provide anonymous visitor behaviour analysis .

How about Anonymous Customer in Store and analysing their behaviour. Companies like Catalina uses the information of buying preferences of customers to drive promotions, merchandizing and sales. Catalina claims their data and insights are unique.

Aggregate data from Customers provide rich information about Brand Preferences etc.


Video Analytics is also common in Retail nowadays. RetailNext, uses video footage to study how shoppers navigate and pushes appropriate messages/promotions

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

How it Works:
Most often the Analytics provider rely on Wifi Pings, 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

Euclid Analytics 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.

+Cisco's Meraki wireless router has a feature called Presence, which has a good location analytics dashboard that measures key anonymous visitor tracking metrics - Capture Rate , PasserBy, Visitors, Median Visit Length, Repeat Visitors etc.

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

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

Real-Time Customer Feedback

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.

How it works?
-- Placing of tablet at the retail outlet with platform agnostic proprietary customer feedback module
-- During the retail journey, customer shares experience through tablet
-- The management accesses real-time dashboard to view customer feedback and take corrective action

Create Right Mood at Right Time using Experience Players 

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. Philips Retail Solutions (PRS) 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

iBeacon and LTE Direct

With more devices on Customer's hands, getting their attention becomes a top priority when they are inside / near the stores

iBeacon
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

LTE Direct
+Qualcomm'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.
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 autonomous discovery

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

This way In-Store (Brick & Mortar) customers can be delighted by leveraging the data from their online experience and vice-versa

Read then Follow Now - How to Chose Right Channel - Using Social Media Analytics

Derive Customer Insights from Social Media Information by Big Data Analytics


Not so long before people (or customers) read newspapers, browsed magazines, visited libraries . Then came Web - people browsed, then came the +Amazon Kindle Fire a Book library in your hands. Now it's an era of Social Media where +LinkedIn , +Twitter and +Facebook have made them as Followers!

Yes people follow a lot - +The Boston Globe , and +Bloomberg News is available on Twitter and Facebook. You can subscribe, follow them . You can follow +CIO , +TechCrunch if you are a technology geek. If you are a marketer then +marketingprofs might be in your following list, +Nike and +adidas will be for a Sports geek

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.

Social Media, Marketing and Segmentation

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.

A simple analysis carried out by a Watch manufacturer shows that those who have bought their premium watches are followers of  GeorgeMichael (+GEORGEMICHAELORG GMORG) Is it time to tap them?

How to Merge Social and Customer Data

Clustering or Segmentation of the data using a combination of Customer, Transactional and Social data is beneficial as it will find homogenous groups.

To arrive at the point - Social media data needs to be aggregated. This is where Big Data comes into picture (Refer How is Apache Hadoop used Big Data Analytics and Inteligence ). Companies like +Hortonworks , +Cloudera Inc provide Hadoop clusters where Social media data can be crunched to get the relevant information out.


Here care must be taken to include/excluded Social data as segmentation variable as it has huge potential to skew the result

Social media information can be used either as :

• Segmentation Variable
• Interpretation variable

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



See also
How to Segment Social Media Users (Influencers / Detractors / Recommenders)

How is Apache Hadoop used Big Data Analytics and Inteligence

Big Data Analytics - Usage of Apache Hadoop / What is the use of Apache Hadoop in an Analytical Project

There are various ways Apache Hadoop is used in a Big Data Project.  +Hortonworks latest report

Apache Hadoop Patterns of Use: Refine, Enrich and ... - Hortonworks categorizes it into

• Data Refinery Pattern
• Data Exploratory Pattern
• Application Enrichment Pattern

In Data Refinery - Hadoop is used for Cleansing up the data and sending the output (probably as aggregation / refinement) to the Enterprise Data Warehouse which might be +Oracle +SQLServer etc

In Data Exploration pattern - 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

In Application Enrichment Pattern 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 .


These are some broad classification of the use of +Apache Hadoop

Free Tools for Data Mining

I 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.

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  Open Source Software - like R,  and also SAS,   +Microsoft Dynamics ERP and SPSS

Segmentation of American Teens Internet Usage

American Teens - Segmentation

Smartphone adoption among American teens has increased substantially and mobile access to the interTeens and Technology 2013 findings. +Teens of America are +Hyperconnected
net is pervasive  by Pew Research Center's

This also shows the predictions for 2020 by +Pew Research Center and +Internet Provider.org

How to Measure Effectiveness of a Campaign using Marketing analytics (Banking)

Marketing Analytics - Measure Effectiveness of Email Campaign for Bank


In our Case Study: Customer Analytics for Telecom Operator to Cross-Sell and Up-Sell 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

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..)

This information is used for personalized marketing through email (This is the Channel for analysis - multiple outbound channels can also be fed) .

Processes in Marketing Analytics for Personalized Promotions for Banking

The processes involved are as follows

1. Gather Data
2. Analyze Data , Document Discovery and Create Model
3  Execute Campaign
4. Collect Responses
5. Measure the Results (Efficiency)
6. Fine tune / Optimize the model
7. Refresh Model and Segment

Since the necessary data for understanding the customer is already available / collected, the data is segmented to understand different customer segments that are available and their profiles

Each segmented is treated in unique way based on their behavioural patterns

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

The most important step after sending those mailers is to collect responses. This is a key differentiator between a good and bad campaign management

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

The Bank's Personalized Campaign has created a 500% increase in response compared to the generic mailer (Refer Figure)

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



The Next Best Action (here the Mailer) is a continuous learning process

+Microsoft Dynamics ERP   was used as the CRM for the Bank. Third party software was used for Mail blast and custom code was used for model development \


There are also custom tools/solutions for campaign / personalized promotion. For example, Manthan Systems' 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

See also:
Payment Card Industry - Crucial for Real-Time Next Best Action (NBA) - Big Data

How to Predict Employee Churn using analytics

How to Know if an Employee is going to Quit before he does

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)

With Lean management .. the human source of information is trimmed and put into better use (really!)

There are various data points that need to be captured to Analyse Employee Churn (We had already spoken a lot about Customer Churn in Customer Attrition Modeling (Analytics))

• Current and Previous Appraisals (this might be a major source)
• Current Pay ?(vis-à-vis Peers and Market)
• Grievances / Issues Reported
• Deviation in Time spent in Office
• Frequency (change) of swipe pattern changes
• Frequency (change) in access to internal information (Intranet etc.)
• Job sites / Social Sites visit patterns (some offices have banned them)
• Feedback from Peers
• Feedback from Supervisors

This list will go on .. Social Media data ...

Employee Churn is costly for the company. It takes months / years to replace the employee with a new one by adequate training etc

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)

SumTotal's Talent Management System is one such system that helps the HR 

Utlimate Software (
www.ultimatesoftware.com) has a tool called Retention Predictor
(TM) for predicting customer Churn

 

How to Get Sales Leads from Analyzing Web Data

Web Pattern Analysis for Identifying Prospects and Products

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.

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

There are many companies /retailers that are using Special algorithms / tools to crawl the web and derive useful insights.


Some specialized companies like Palo Alto based Infer (https://www.infer.com/) offer an analysis software that can be linked to CRM system like SalesForce (http://www.salesforce.com/)a and rank the customer



Infer's ranking system uses more than 150 signals , which includes many data feeds - Census, Job Boards, Tweets , Facebook Likes and Comments



There are many algorithms that help in analysing the Facebook data

OpenGraph API is one of them


 See Also:

How to Segment Social Media Users (Influencers / Detractors / Recommenders)

How to measure Price Sensitity of Customers

Segmentation Standards / Framework

Payment Marketing Analytics - Something to Watchout in 2013

How to Push Messages Real-Time at Point-of-Sale or Payment

Payment Marketing is catching up now. This provides the Bank / Retailer to push messages / offers on real-time to their customers.

What is Payment Marketing?

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.

We have already seen the importance of Payment card companies in the field of marketing. This is another layer of it

How it Works?

The lifecycle of Payment Marketing revolves around understanding the customer through analytics. Swipely, 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
system, which can be used to

• Send Personalized Messages (Thank you message etc)
• Cross-Sell products/Services
• Inform corrective actions

The above can be expanded based on NBA strategy. The advantages of Swipely is the ease of upgrading - no hardware / software is required and no changes in customer's payment m

echanism

DriveItNow uses the Credit, Criteria and Collateral to provide real payments

How does External Factors Affect Next Best Action (NBA) - Timely Promotions

What is (NOT) the Right Time for Pushing Promotional Messages

We have already had a look at the methods to identify the right time from customer segmentation or from propensity models

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.

For example, pushing a promotional message during Boston Marathon is an example for NOT pushing promotions.

Business Rules and Next Best Action

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 Drools that can be used to create and maintain business rules .

How to use OLAP for interpreting Cluster Results

How to Intepret Clustering Results / K-means Cluster output using Data Warehouse

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

K-means (or any other method) clustering partitions the data into groups that are homogeneous with respected to the cluster variables.

The output mostly would be the primary variable, and its associated cluster along with other cluster / segmentation variables

Cluster Profiling / Interpretation

Though cluster output and their scatter plot provides some interesting findings, it's the cluster profiling that helps the user in a better way

OLAP and Data Warehousing

OLAP  is an BI (Business Intelligence) approach to answering multi-dimensional analytical queries in real or near-real time

OLAP consists of Facts, Fact Tables, Dimension tables, Cubes that contains the precise data for a given requirement etc.

OLAP and Clustering

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

In similar way decision tree results can also be fed back to OLAP (+Oracle , +SQL Server , +Terradata AG )

How to Segment Social Media Users (Influencers / Detractors / Recommenders)

Segmentation of Social Media Influencers

We have seen in the past about the Retail Specific Segmentation Standards and also some Segmentation Tools that help to achieve that.

Here we would delve bit deep into segmenting the social media users.

Behavioral Segmentation of Social Media Users

Social media users are classified as shown by the Klout Influencer Matrix given below

Depending on the Need / Goal, one can select the specific segment of users. IBM's Social Analytics Tool (SPSS) helps to identify the following from Social Data

• Influencers
• Recommenders
• Detractors

The above combined with customer and transaction data would give necessary insights into customer behavior

Merging Social Data with CRM / Customer Data

The social users can also be segmented by demographics, geographics, which would provide information that might not be captured in CRM (for example, +Microsoft Dynamics ERP )

The 7 elements of social data

Sandile Mayambala a digital analyst as come up with the following combinations

• demographic
• product
• psychographic
• behavioral
• referrals
• location
• intention

It may not be possible to get all data points for every customer. In that case the data is normalized and analyzed

See also :How to Find Social Influencers using analytics,
Five Types of Social Media Influencers

Link-Selling Analytics (Web Analytics)

How does Analytics help efficient Link-Selling

Link-Selling is a form of cross-selling ,
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.

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.

Though mostly the logic is rule-based, use of Predictive modeling increases accuracy

Customer Analytics - Understand Mood of the Day

How to Analyze Customer Behavioral Changes on Time (Day)






 Netflix - 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

• Past behavior (view history)
• Product rating
• Recent comparison

Cinematch uses Nearest Neighbor method for predicting a movie

The company decided to have an Open contest to fine tune the recommendations (or the Next Best Action if you wanted it to be called so) - the winner would be the one who beat the recommendation of Cinematch by 10%.

AT&T with the combination of nearest neighbor , singular value decomposition (SVD) methods were able to win the one


Please have a look at http://www.research.att.com/articles/featured_stories/2010_01/2010_02_netflix_article.html?fbid=8rnpOtsYzRv for the full text.

Widely used Segmentation Products / Solutions

Free Segmentation Frameworks / Products

We had an indepth analysis of various segmentation frameworks for profiling customers in Segmentation Standards / Framework. Here we will look in more detail on some readily available Segmentation products that will accelerate segmentation/clustering.



Prizm's market segmentation comes-up with beautiful segments for a particular Zipcode. If you want to open a Store in the locality ZIP Code 65231, Auxvasse, MO. Here are the results from the search (http://www.claritas.com/MyBestSegments/Default.jsp?ID=20#)

PersonicX 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.





Forrester's Social Technographics data classifies consumers into seven overlapping levels of social technology participation. Based on their proprietary Consumer Technographics survey data, they can
share with how social participation varies among your consumers globally and help plan a targeted social technology strategy.

+Monetate'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
instantly take action by targeting offers and content specifically to those segments

+OfficeMax is using LivePredict to identify highest and lowest performing segments at both brand and campaign levels

Creating Valuable Data Columns - Aggregate Data

How to create insightful summary data from Operational Data

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.

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.

Some days back we were looking at the importance of Relative Pricing in Customer Analytics. Another real world example would be the Bizocity scores used by AT&T

Bizocity score takes into account the originating call number, the destination, the duration etc to arrive at the score.

See also: Case Study: Customer Analytics for Telecom Operator to Cross-Sell and Up-Sell

Customer Analytics - Relative Price as Data Point

Relative Pricing in Customer Behaviour Analytics

We had some discussion on Price Sensitivity earlier. This was used for determining the Right Price of offer for that customer. However, the price sensitivity is more related to Demand Elasticity

Relative Price is the price of a product/service with respect to another product/service. The latter one is usually termed as the base product/service.

How to use Relative Price to understand Customer Behaviour

Relative price provides very much useful insight about the customer's behaviour. The following would be the typical values for Relative price

• High
• Medium
• Low

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
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)

Cust ID	Category	Premium	High	Medium	Low
RF0000123	OVGT120980	0	6	16	0
RF0000227	OVGT120980	11	3	2	0

Relative Pricing Customer Table

)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.

The above methodology can be used and the following can be used as Segmentation variables

• No of High Value Items
• No of Medium Value items
• No of Low Value items

Please try this out and let us know the difference it brought to your segments

How to measure effectiveness of Switcher Campaigns in Retail 

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.

dunnhumby's 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

Case Study: Customer Analytics for Telecom Operator to Cross-Sell and Up-Sell

How to find products/services to Cross-Sell / Up-Sell using Customer analytics / NBO

The Telecom operator has a good customer base and wants to drive more sales using existing customers. The operator decided to craft a NBO strategy for increasing sales from existing customers (this is not just retaining the customer - by reducing Churn)

As with any NBO - the first step is to determine the Objective

Step 1: Define The Objective

The objective here is - Increase sales from existing customer through cross-sell or up-sell

A customer with two or more services is four times less likely to Churn than a customer with a singl service - this means that cross-sell not only increases the incremental sales but also increases Loyalty. The strategic objectives like these should be driving the NBO objective

With the goal being defined very clearly, the next step is to collect required data for the NBO

Step 2: Collect Data

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.

The entry channel (the channel through which the customer was acquired) would be a vital information.

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.

If the internal data collection is done, one can look for Syndicate data or External Data (Payment Card data)

Step 3: Analyze, Model  and Execute

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 Prizm. This should be a good input for rolling up data

Understanding the customer is a first stage in NBO. The customer's behavioral attributes are
analyzed using statistical analysis (clustering, link analysis, decision trees), predictive modelling etc.

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. Understanding the Service/Product Offering is the next stage .

For example,

• Wireless devices
• WiFi Services
• VOIP Call services
• Local call services
• Broadband Direct connection
• loud hosting

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.

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.

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 appropriate context.

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.



Tools like SAS and SPSS can help in achieving this faster. There are Open Source Software - like R, which is catching up fast

Step 4: Measure and Recalibrate

Every offer that is sent is an Test Offer. 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.

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.

Next Best Offer Solution Framework

This is a continous cycle and the role of Statisticans, Business Leaders play an important role