mlsanityData to 7 Oct 2026

The Diversity Paradox revisited: Systemic Effects of Feedback Loops in Recommender Systems

arXiv 2602.16315 ↗First posted 18 Feb 2026cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recommender systems shape individual choices through feedback loops in which user behavior and algorithmic recommendations coevolve over time. The systemic effects of these loops remain poorly understood, in part due to unrealistic assumptions in existing simulation studies. We propose a feedback-loop model that captures implicit feedback, periodic retraining, probabilistic adoption of recommendations, and heterogeneous recommender systems. We apply the framework on online retail and music streaming data and analyze systemic effects of the feedback loop. We find that increasing recommender adoption may lead to a progressive diversification of individual consumption, while collective demand is redistributed in model- and domain-dependent ways, often amplifying popularity concentration. Temporal analyses further reveal that apparent increases in individual diversity observed in static evaluations are illusory: when adoption is fixed and time unfolds, individual diversity consistently decreases across all models. Our results highlight the need to move beyond static evaluations and explicitly account for feedback-loop dynamics when designing recommender systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 54 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

20 of 54 references.

References · 20

  1. 2017Neural Collaborative Filteringcited by 1,108
  2. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
  3. 2019Neural Graph Collaborative Filteringcited by 660
  4. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 326
  5. 2020Self-supervised Graph Learning for Recommendationcited by 305
  6. 2017How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utilitycited by 116
  7. 2020Feedback Loop and Bias Amplification in Recommender Systemscited by 89
  8. 2017Boltzmann Exploration Done Rightcited by 69
  9. 2019Degenerate Feedback Loops in Recommender Systemscited by 67
  10. 2022RecBole 2.0: Towards a More Up-to-Date Recommendation Librarycited by 39
  11. 2018Spectral Collaborative Filteringcited by 34
  12. 2023Human-AI Coevolutioncited by 27
8 more
  1. 2021Measuring Recommender System Effects with Simulated Userscited by 20
  2. 2024Agentic Feedback Loop Modeling Improves Recommendation and User Simulationcited by 16
  3. 2020Popularity Bias in Recommendation: A Multi-stakeholder Perspectivecited by 6
  4. 2020The Engagement-Diversity Connection: Evidence from a Field Experiment on Spotifycited by 5
  5. 2024Algorithmic Drift: A Simulation Framework to Study the Effects of Recommender Systems on User Preferencescited by 5
  6. 2023Interactive Content Diversity and User Exploration in Online Movie Recommenders: A Field Experimentcited by 4
  7. 2024A survey on the impacts of recommender systems on users, items, and human-AI ecosystemscited by 3
  8. 2024Flexible Generation of Preference Data for Recommendation Analysiscited by 2

Built on by

Not cited yet.