# Existence conditions for hidden feedback loops in online recommender systems

arXiv: https://arxiv.org/abs/2109.05278 · HTML: https://mlsanity.com/paper/2109.05278/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 11 Sep 2021.

## Builds on (most cited first, 7 of 7)

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling](https://mlsanity.com/paper/1802.09127/) (2018)
- [Degenerate Feedback Loops in Recommender Systems](https://mlsanity.com/paper/1902.10730/) (2019)
- [Hidden Incentives for Auto-Induced Distributional Shift](https://mlsanity.com/paper/2009.09153/) (2020)
- [Taming Non-stationary Bandits: A Bayesian Approach](https://mlsanity.com/paper/1707.09727/) (2017)
- [A Survey of Online Experiment Design with the Stochastic Multi-Armed Bandit](https://mlsanity.com/paper/1510.00757/) (2015)
- [Analysis of hidden feedback loops in continuous machine learning systems](https://mlsanity.com/paper/2101.05673/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems](https://mlsanity.com/paper/2405.02726/) (2024)

## Abstract (arXiv)

We explore a hidden feedback loops effect in online recommender systems. Feedback loops result in degradation of online multi-armed bandit (MAB) recommendations to a small subset and loss of coverage and novelty. We study how uncertainty and noise in user interests influence the existence of feedback loops. First, we show that an unbiased additive random noise in user interests does not prevent a feedback loop. Second, we demonstrate that a non-zero probability of resetting user interests is sufficient to limit the feedback loop and estimate the size of the effect. Our experiments confirm the theoretical findings in a simulated environment for four bandit algorithms.