New DPFR method jointly evaluates recommender system fairness and relevance

Researchers have introduced a new method called Distance to Pareto Frontier (DPFR) for jointly evaluating the fairness and relevance of recommender systems. This approach addresses limitations in existing methods that either evaluate these aspects in isolation or provide an imbalanced joint assessment. DPFR utilizes a Pareto frontier of relevance and fairness scores to represent optimal trade-offs, offering a modular and intuitive joint score. Experiments on multiple datasets and recommenders indicate that DPFR is more robust than current joint evaluation techniques and provides guidelines for its effective use. AI

IMPACT Provides a more robust framework for evaluating AI-driven recommender systems, potentially improving user experience and ethical considerations.

RANK_REASON Academic paper introducing a new evaluation method for recommender systems. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• Distance to Pareto Frontier (DPFR)
• Recommender Systems
• Theresia Veronika Rampisela

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →