Managing Popularity Bias in Recommender Systems with Personalized Re-ranking

TL;DR

This paper presents a personalized re-ranking method to reduce popularity bias in recommender systems, increasing long-tail item recommendations without significantly sacrificing accuracy.

Contribution

It introduces a post-processing re-ranking approach that enhances long-tail item coverage, outperforming existing regularization-based methods.

Findings

Effective management of popularity bias demonstrated

Improved long-tail item coverage over baseline methods

Maintains recommendation accuracy while diversifying outputs

Abstract

Many recommender systems suffer from popularity bias: popular items are recommended frequently while less popular, niche products, are recommended rarely or not at all. However, recommending the ignored products in the `long tail' is critical for businesses as they are less likely to be discovered. In this paper, we introduce a personalized diversification re-ranking approach to increase the representation of less popular items in recommendations while maintaining acceptable recommendation accuracy. Our approach is a post-processing step that can be applied to the output of any recommender system. We show that our approach is capable of managing popularity bias more effectively, compared with an existing method based on regularization. We also examine both new and existing metrics to measure the coverage of long-tail items in the recommendation.