# Deviation-Based Learning: Training Recommender Systems Using Informed User Choice

arXiv: https://arxiv.org/abs/2109.09816 · HTML: https://mlsanity.com/paper/2109.09816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 33 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 3 of 3)

- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Contextual Inverse Optimization: Offline and Online Learning](https://mlsanity.com/paper/2106.14015/) (2021)
- [Deconvolving Feedback Loops in Recommender Systems](https://mlsanity.com/paper/1703.01049/) (2017)

## Abstract (arXiv)

This paper proposes a new approach to training recommender systems called deviation-based learning. The recommender and rational users have different knowledge. The recommender learns user knowledge by observing what action users take upon receiving recommendations. Learning eventually stalls if the recommender always suggests a choice: Before the recommender completes learning, users start following the recommendations blindly, and their choices do not reflect their knowledge. The learning rate and social welfare improve substantially if the recommender abstains from recommending a particular choice when she predicts that multiple alternatives will produce a similar payoff.