A Two-Stage Calibration Approach for Mitigating Bias and Fairness in Recommender Systems

• DOI: 10.1145/3605098.3636092
• Publication Date: 2024-05-21T17:59:16Z
• Authors: Rodrigo Souza; Marcelo Manzato

Popularity bias and unfairness are problems caused by the lack of calibration in recommender systems. Works that intend to reduce effect popularity do not consider distribution item genres/categories users' profiles. Other studies aim calibrate system generate fair recommendations according profiles, but usually still biased towards popularity. We propose a approach based on preferences for different levels items their genres. The proposed works post-processing stage can be combined with recommendation models. evaluated offline experiments using one state-of-the-art dataset, three algorithms, six baselines, metrics popularity, fairness, accuracy. results indicate reduced improved fairness.