Popularity-Aware Item Weighting for Long-Tail Recommendation

2018/02/15 by Himan Abdollahpouri, Abdollahpouri, Himan, Robin Burke +3
Business, Management and Accounting · Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #Consumer Market Behavior and Pricing #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.1802.05382

openalex publication_date 2018/02/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Many recommender systems suffer from the popularity bias problem: popular items are being recommended frequently while less popular, niche products, are recommended rarely if not at all. However, those ignored products are exactly the products that businesses need to find customers for and their recommendations would be more beneficial. In this paper, we examine an item weighting approach to improve long-tail recommendation. Our approach works as a simple yet powerful add-on to existing recommendation algorithms for making a tunable trade-off between accuracy and long-tail coverage.

Citations

• BPR: Bayesian Personalized Ranking from Implicit Feedback

Related

• Managing Popularity Bias in Recommender Systems with Personalized Re-ranking
• Reducing Popularity Bias in Recommendation Over Time
• Considering user dynamic preferences for mitigating negative effects of long tail in recommender systems
• A Generic Top-N Recommendation Framework For Trading-off Accuracy, Novelty, and Coverage
• The Unfairness of Popularity Bias in Recommendation