Popularity Bias in Ranking and Recommendation

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. Popularity bias is also against social justice where the entities need to have a fair chance of being served and represented. In this work, I investigate the problem of popularity bias in recommender systems and develop algorithms to address this problem.