Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience

TL;DR

This paper introduces a novel two-stage ranking framework combining contextual bandits with diversity to optimize widget placement on mobile e-commerce homepages, enhancing user engagement and personalization.

Contribution

It proposes a new approach modeling widget ranking as a contextual bandit problem with diversity, tailored for dynamic and heterogeneous e-commerce environments.

Findings

Improved widget ranking effectiveness demonstrated through offline experiments.

Enhanced user engagement shown by online A/B testing on Myntra.

Effective handling of dynamic widget sets and delayed feedback.

Abstract

In the realm of e-commerce, popular platforms utilize widgets to recommend advertisements and products to their users. However, the prevalence of mobile device usage on these platforms introduces a unique challenge due to the limited screen real estate available. Consequently, the positioning of relevant widgets becomes pivotal in capturing and maintaining customer engagement. Given the restricted screen size of mobile devices, widgets placed at the top of the interface are more prominently displayed and thus attract greater user attention. Conversely, widgets positioned further down the page require users to scroll, resulting in reduced visibility and subsequent lower impression rates. Therefore it becomes imperative to place relevant widgets on top. However, selecting relevant widgets to display is a challenging task as the widgets can be heterogeneous, widgets can be introduced or removed at any given time from the platform. In this work, we model the vertical widget reordering as a contextual multi-arm bandit problem with delayed batch feedback. The objective is to rank the vertical widgets in a personalized manner. We present a two-stage ranking framework that combines contextual bandits with a diversity layer to improve the overall ranking. We demonstrate its effectiveness through offline and online A/B results, conducted on proprietary data from Myntra, a major fashion e-commerce platform in India.