NER: Nash Entropy-Regularised Scoring for Diversity-Aware Collaborative Filtering

Q: What does this research mean for the field?

Adding an entropy-based diversity reward to Nash Bargaining Solution (NBS) collaborative filtering mitigates structural popularity bias and significantly improves recommendation accuracy, yielding up to a 5.6-fold increase in precision. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Assil KHELIFI

doi:10.5281/zenodo.19154440

March 21, 2026Open Access

NER: Nash Entropy-Regularised Scoring for Diversity-Aware Collaborative Filtering

View Full Paper

Ask AI

Bookmark

Share

Key Points

The study aims to enhance recommendation systems by incorporating a diversity scoring approach that balances item popularity and audience engagement.
Developed Nash Entropy-Regularised Scoring (NER) for diverse item recommendations.
Analyzed item popularity bias and proposed an entropy bonus to reward diverse ratings.
Evaluated performance using datasets such as ML-100K and compared against symmetric NBS.
NER outperformed previous methods, achieving a Precision@10 of 0.0827.
Demonstrated a 5.6× improvement in recommendation accuracy over symmetric NBS.
Identified optimal γ value of 0.3 for enhancing diversity in recommendations.

Implication

NBS demonstrates improved recommendation diversity in collaborative filtering, suggesting effective alternatives to popularity penalties.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Assil KHELIFI (2026) studied this question.

synapsesocial.com/papers/69c0e051fddb9876e79c1c96 https://doi.org/10.5281/zenodo.19154440

View Full Paper

Ask AI

Bookmark

Share

NER: Nash Entropy-Regularised Scoring for Diversity-Aware Collaborative Filtering

Key Points

Implication

Abstract

Discussion

Cite This Study

NER: Nash Entropy-Regularised Scoring for Diversity-Aware Collaborative Filtering

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading