Himan Abdollahpouri

Controlling Popularity Bias in Learning-to-Rank Recommendation

2017

Many recommendation algorithms suffer from popularity bias in their output: popular items are recommended frequently and less popular ones rarely, if at all. However, less popular, long-tail items are precisely those that are often desirable …

Managing Popularity Bias in Recommender Systems with Personalized Re-Ranking.

2019 · arXiv (Cornell University)

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 …