Personalized Recommendation System Design for an Online B2B Platform

We formulate the problem of designing a personalised recommendation system for an online business-to-business (B2B) marketplace, propose a method to solve it, and evaluate results using field experiments. In this problem, buyers place requests for quotation (RFQs) to the platform, sellers respond by accepting or declining those RFQs, and the objective of the platform is to design a recommendation system by matching RFQs with sellers based on likelihood of acceptance. Our research is conducted in collaboration with IndiaMart, the dominant online B2B platform in India serving approximately 119 million buyer firms and 6.4 million seller firms in more than 71 million products and services. The main challenges in our problem is of class imbalance such that the volume of `accepted’ records is significantly larger than `declined’ records. We develop a new resampling approach, Panel Data Augmentation Technique, to counter this problem, and construct an aggregate measure based on operational costs to determine the optimal resampling strategy. Our results demonstrate a high out-of-sample predictive accuracy and a significant gain in the recall for minority class in offline testing. We further report results from two controlled field experiments conducted at IndiaMart to show the benefits in practise.