# Feedback Loop and Bias Amplification in Recommender Systems

arXiv: https://arxiv.org/abs/2007.13019 · HTML: https://mlsanity.com/paper/2007.13019/

## Key facts

- Cited by 90 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2020.

## Built on by (most cited first, 30 of 90)

- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [On Generative Agents in Recommendation](https://mlsanity.com/paper/2310.10108/) (2023)
- [Feedback Loops With Language Models Drive In-Context Reward Hacking](https://mlsanity.com/paper/2402.06627/) (2024)
- [Leveraging Large Language Models in Conversational Recommender Systems](https://mlsanity.com/paper/2305.07961/) (2023)
- [Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet](https://mlsanity.com/paper/2306.06130/) (2023)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [User-centered Evaluation of Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2103.06364/) (2021)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Estimating and Penalizing Induced Preference Shifts in Recommender Systems](https://mlsanity.com/paper/2204.11966/) (2022)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Performative Reinforcement Learning](https://mlsanity.com/paper/2207.00046/) (2022)
- [Human-AI Coevolution](https://mlsanity.com/paper/2306.13723/) (2023)
- [Preference Dynamics Under Personalized Recommendations](https://mlsanity.com/paper/2205.13026/) (2022)
- [StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random](https://mlsanity.com/paper/2205.04701/) (2022)
- [Fair ranking: a critical review, challenges, and future directions](https://mlsanity.com/paper/2201.12662/) (2022)
- [How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective](https://mlsanity.com/paper/2404.12008/) (2024)
- [Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey](https://mlsanity.com/paper/2504.10499/) (2025)
- [Correcting Exposure Bias for Link Recommendation](https://mlsanity.com/paper/2106.07041/) (2021)
- [Agentic Feedback Loop Modeling Improves Recommendation and User Simulation](https://mlsanity.com/paper/2410.20027/) (2024)
- [LLMs for User Interest Exploration in Large-scale Recommendation Systems](https://mlsanity.com/paper/2405.16363/) (2024)
- [A Graph-based Approach for Mitigating Multi-sided Exposure Bias in Recommender Systems](https://mlsanity.com/paper/2107.03415/) (2021)
- [Breaking Feedback Loops in Recommender Systems with Causal Inference](https://mlsanity.com/paper/2207.01616/) (2022)
- [Experiments on Generalizability of User-Oriented Fairness in Recommender Systems](https://mlsanity.com/paper/2205.08289/) (2022)
- [Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations](https://mlsanity.com/paper/2302.06676/) (2023)
- [Speciesist bias in AI -- How AI applications perpetuate discrimination and unfair outcomes against animals](https://mlsanity.com/paper/2202.10848/) (2022)
- [Characterizing and modeling harms from interactions with design patterns in AI interfaces](https://mlsanity.com/paper/2404.11370/) (2024)
- [Accounting for AI and Users Shaping One Another: The Role of Mathematical Models](https://mlsanity.com/paper/2404.12366/) (2024)
- [The Lock-in Hypothesis: Stagnation by Algorithm](https://mlsanity.com/paper/2506.06166/) (2025)
- [Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach](https://mlsanity.com/paper/2109.08549/) (2021)
- [Diversified Recommendations for Agents with Adaptive Preferences](https://mlsanity.com/paper/2210.07773/) (2022)

## Abstract (arXiv)

Recommendation algorithms are known to suffer from popularity bias; a few popular items are recommended frequently while the majority of other items are ignored. These recommendations are then consumed by the users, their reaction will be logged and added to the system: what is generally known as a feedback loop. In this paper, we propose a method for simulating the users interaction with the recommenders in an offline setting and study the impact of feedback loop on the popularity bias amplification of several recommendation algorithms. We then show how this bias amplification leads to several other problems such as declining the aggregate diversity, shifting the representation of users' taste over time and also homogenization of the users experience. In particular, we show that the impact of feedback loop is generally stronger for the users who belong to the minority group.