Counterfactual Reciprocal Recommender Systems for User-to-User Matching

TL;DR

This paper presents CFRR, a causal framework for reciprocal recommender systems that reduces bias from popularity effects, improving fairness and accuracy in user-to-user matching.

Contribution

CFRR introduces a novel causal approach using inverse propensity scoring to mitigate popularity bias in reciprocal recommender systems.

Findings

Improves NDCG@10 by up to 3.5%

Increases long-tail user coverage by up to 51%

Reduces Gini exposure inequality by up to 24%

Abstract

Reciprocal recommender systems (RRS) in dating, gaming, and talent platforms require mutual acceptance for a match. Logged data, however, over-represents popular profiles due to past exposure policies, creating feedback loops that skew learning and fairness. We introduce Counterfactual Reciprocal Recommender Systems (CFRR), a causal framework to mitigate this bias. CFRR uses inverse propensity scored, self-normalized objectives. Experiments show CFRR improves NDCG@10 by up to 3.5% (e.g., from 0.459 to 0.475 on DBLP, from 0.299 to 0.307 on Synthetic), increases long-tail user coverage by up to 51% (from 0.504 to 0.763 on Synthetic), and reduces Gini exposure inequality by up to 24% (from 0.708 to 0.535 on Synthetic). CFRR offers a promising approach for more accurate and fair user-to-user matching.