Contrastive Learning for Diversity-Aware Product Recommendations in Retail
Preprint
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Fairness and Diversity in Recommender Systems: A SurveyACM Transactions on Intelligent Systems and Technology, 2025
- Metrics for Popularity Bias in Dynamic Recommender Systems2024
- Quality Metrics in Recommender Systems: Do We Calculate Metrics Consistently?2021
- Measuring the Business Value of Recommender SystemsACM Transactions on Management Information Systems, 2019
- Approximate Nearest Neighbor Search on High Dimensional Data — Experiments, Analyses, and ImprovementIEEE Transactions on Knowledge and Data Engineering, 2019
- Beyond accuracy2010