Existence conditions for hidden feedback loops in online recommender systems
arXiv:2109.05278 · doi:10.1007/978-3-030-91560-5_19
Abstract
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.
6 pages, 3 figures
References in corpus (5)
- Degenerate Feedback Loops in Recommender Systems
- A Survey of Online Experiment Design with the Stochastic Multi-Armed Bandit
- Taming Non-stationary Bandits: A Bayesian Approach
- Analysis of hidden feedback loops in continuous machine learning systems
- Hidden Incentives for Auto-Induced Distributional Shift