How to Identify Right Shopper for Promotions / How to Categorize Shoppers based on Loyalty

Identify Profitable Shoppers using Statistical Modeling

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 What are the steps in NBO (Next Best Offer) to give Personalized Promotion and Find Right Channel 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

Well before attaching an offer to the customer, one needs to select if the customer is profitable for the loyalty program

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

CLV and NPV are some techniques to use in the current scenario. Segmentation of customers based on the above would provide a good insights

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. Price plays an important role in this

According to a study by +McKinsey on Marketing & Sales 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

Sports Analytics - Use of Big Data Analytics in Sports

Sports Analytics - The next use case for Big Data Analytics

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.

Not anymore. Though their height, weight and the fitness were measured earlier .. the new Big Data analytics stores every

SaberMetrics - the Bellwether 

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.

THere are many sports and games wHere analytiCs an Help, for example, Tennis

Understanding tHe player's potential would Help the manager fine tune the player

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