Adaptive, Personalized Diversity for Visual Discovery

TL;DR

This paper introduces an adaptive, personalized visual browsing system that enhances user engagement by combining relevance scoring, diversification, and user preference learning, leading to improved click-through rates and session durations.

Contribution

It presents a novel system integrating Bayesian relevance scoring, submodular diversification, and personalized preferences for visual discovery in e-commerce.

Findings

Significant increase in click-through-rate on live traffic.

Extended session durations indicate higher user engagement.

Effective personalization improves browsing experience.

Abstract

Search queries are appropriate when users have explicit intent, but they perform poorly when the intent is difficult to express or if the user is simply looking to be inspired. Visual browsing systems allow e-commerce platforms to address these scenarios while offering the user an engaging shopping experience. Here we explore extensions in the direction of adaptive personalization and item diversification within Stream, a new form of visual browsing and discovery by Amazon. Our system presents the user with a diverse set of interesting items while adapting to user interactions. Our solution consists of three components (1) a Bayesian regression model for scoring the relevance of items while leveraging uncertainty, (2) a submodular diversification framework that re-ranks the top scoring items based on category, and (3) personalized category preferences learned from the user's behavior. When tested on live traffic, our algorithms show a strong lift in click-through-rate and session duration.