# Correcting the User Feedback-Loop Bias for Recommendation Systems

arXiv: https://arxiv.org/abs/2109.06037 · HTML: https://mlsanity.com/paper/2109.06037/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 10 of 10)

- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility](https://mlsanity.com/paper/1710.11214/) (2017)
- [A Simple Convolutional Generative Network for Next Item Recommendation](https://mlsanity.com/paper/1808.05163/) (2018)
- [Causal Embeddings for Recommendation](https://mlsanity.com/paper/1706.07639/) (2017)
- [Modeling User Exposure in Recommendation](https://mlsanity.com/paper/1510.07025/) (2015)
- [Sequential Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1811.09975/) (2018)
- [Estimating the Causal Impact of Recommendation Systems from Observational Data](https://mlsanity.com/paper/1510.05569/) (2015)
- [Human Interaction with Recommendation Systems](https://mlsanity.com/paper/1703.00535/) (2017)
- [Collaborative Filtering with Social Exposure: A Modular Approach to Social Recommendation](https://mlsanity.com/paper/1711.11458/) (2017)

## Built on by (most cited first, 5 of 5)

- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Breaking Feedback Loops in Recommender Systems with Causal Inference](https://mlsanity.com/paper/2207.01616/) (2022)
- [Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach](https://mlsanity.com/paper/2310.17496/) (2023)
- [Counterfactual Augmentation for Multimodal Learning Under Presentation Bias](https://mlsanity.com/paper/2305.14083/) (2023)
- [Counterfactual Reciprocal Recommender Systems for User-to-User Matching](https://mlsanity.com/paper/2508.01867/) (2025)

## Abstract (arXiv)

Selection bias is prevalent in the data for training and evaluating recommendation systems with explicit feedback. For example, users tend to rate items they like. However, when rating an item concerning a specific user, most of the recommendation algorithms tend to rely too much on his/her rating (feedback) history. This introduces implicit bias on the recommendation system, which is referred to as user feedback-loop bias in this paper. We propose a systematic and dynamic way to correct such bias and to obtain more diverse and objective recommendations by utilizing temporal rating information. Specifically, our method includes a deep-learning component to learn each user's dynamic rating history embedding for the estimation of the probability distribution of the items that the user rates sequentially. These estimated dynamic exposure probabilities are then used as propensity scores to train an inverse-propensity-scoring (IPS) rating predictor. We empirically validated the existence of such user feedback-loop bias in real world recommendation systems and compared the performance of our method with the baseline models that are either without de-biasing or with propensity scores estimated by other methods. The results show the superiority of our approach.