Contrastive Learning for Diversity-Aware Product Recommendations in Retail

TL;DR

This paper presents a contrastive learning approach that improves diversity and catalog coverage in retail recommender systems while maintaining recommendation quality, addressing popularity bias in large-scale online retail environments.

Contribution

It introduces a contrastive learning method with negative sampling to enhance diversity in product recommendations without sacrificing accuracy.

Findings

Increased catalog coverage in recommendations.

Maintained strong recommendation performance.

Improved diversity in online retail settings.

Abstract

Recommender systems often struggle with long-tail distributions and limited item catalog exposure, where a small subset of popular items dominates recommendations. This challenge is especially critical in large-scale online retail settings with extensive and diverse product assortments. This paper introduces an approach to enhance catalog coverage without compromising recommendation quality in the existing digital recommendation pipeline at IKEA Retail. Drawing inspiration from recent advances in negative sampling to address popularity bias, we integrate contrastive learning with carefully selected negative samples. Through offline and online evaluations, we demonstrate that our method improves catalog coverage, ensuring a more diverse set of recommendations yet preserving strong recommendation performance.