Abstract 

Bigbasket.com was India’s largest online grocery and food store established in 2011 by a group of entrepreneurs Hari Menon, Vipul Parekh, V S Ramesh, V S Sudhakar, and Abhinay Choudhari. In 2016, Bigbasket sold more than 18,000 products and 1,000 brands operating across 12 Indian cities. Online grocery market in India has been small, but a rapidly growing segment. According to “The Retailer” Ernst and Young’s publication in consumer products and retail sector, during July–September 2015, India was among the top-10 food and grocery markets in the world, with an estimated size of INR 22.5 trillion (approximately USD 350 billion). The market has grown at 10–12% CAGR between 2010 and 2015, with food and grocery being the largest segment, accounting for close to 60% in 2015 alone.

The protagonist of the case, Pramod Jajoo, Chief Technology Officer, at Bigbasket was trying to solve two problems frequently encountered by customers of online grocery stores. It was estimated that about 30% of Bigbasket customers place orders through smart phones. Unlike other e-commerce companies such as Amazon, Bigbasket customers place order for several products in a single order, sometimes as high as 80 in one order depending on their purchase frequency. When the basket size is high, using smart phones to place order is challenging. Also, it is a common phenomenon that customers forget to place order few grocery items which may result either in placing additional orders or customers purchasing those products from neighborhood stores resulting in a financial loss to online grocery stores.

 Jajoo and his team wanted to create a “Smart Basket” that would make placing orders easier for their customers and “Did you forget?” feature that would identify the items the customer may have forgotten to order.

Learning Objective 

The case may be used in Business Analytics and Big Data courses of MBA or Executive MBA programs to teach recommender systems. The learning objectives are:

1. Importance of recommender systems in the retail context, especially e-commerce.
2. Learn different recommender system models such as content-based and knowledge-based.
3. Understand similarity measures such as cosine similarity, Jaccard coefficient, and Dice coefficient.
4. Learn innovative models that can be used for product recommendation such as page ranking algorithm.