# Recommendations as Treatments: Debiasing Learning and Evaluation

arXiv: https://arxiv.org/abs/1602.05352 · HTML: https://mlsanity.com/paper/1602.05352/

## Key facts

- Cited by 248 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2016.

## Built on by (most cited first, 30 of 248)

- [Data Distillation: A Survey](https://mlsanity.com/paper/2301.04272/) (2023)
- [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://mlsanity.com/paper/2303.05453/) (2023)
- [AutoDebias: Learning to Debias for Recommendation](https://mlsanity.com/paper/2105.04170/) (2021)
- [ESCM2: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation](https://mlsanity.com/paper/2204.05125/) (2022)
- [Causal Matrix Completion](https://mlsanity.com/paper/2109.15154/) (2021)
- [CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation](https://mlsanity.com/paper/2403.06447/) (2024)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [SurvTRACE: Transformers for Survival Analysis with Competing Events](https://mlsanity.com/paper/2110.00855/) (2021)
- [Understanding the role of importance weighting for deep learning](https://mlsanity.com/paper/2103.15209/) (2021)
- [Anticipating Performativity by Predicting from Predictions](https://mlsanity.com/paper/2208.07331/) (2022)
- [Generalized Strategic Classification and the Case of Aligned Incentives](https://mlsanity.com/paper/2202.04357/) (2022)
- [Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequality](https://mlsanity.com/paper/2212.09900/) (2022)
- [A Trip Towards Fairness: Bias and De-Biasing in Large Language Models](https://mlsanity.com/paper/2305.13862/) (2023)
- [Identifiable Generative Models for Missing Not at Random Data Imputation](https://mlsanity.com/paper/2110.14708/) (2021)
- [RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents](https://mlsanity.com/paper/2308.09904/) (2023)
- [Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation](https://mlsanity.com/paper/2105.13623/) (2021)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random](https://mlsanity.com/paper/2205.04701/) (2022)
- [Policy Learning with Adaptively Collected Data](https://mlsanity.com/paper/2105.02344/) (2021)
- [Top-N Recommendation with Counterfactual User Preference Simulation](https://mlsanity.com/paper/2109.02444/) (2021)
- [A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions](https://mlsanity.com/paper/2109.03540/) (2021)
- [Fair ranking: a critical review, challenges, and future directions](https://mlsanity.com/paper/2201.12662/) (2022)
- [Trustworthy Recommender Systems](https://mlsanity.com/paper/2208.06265/) (2022)
- [How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective](https://mlsanity.com/paper/2404.12008/) (2024)
- [Infinite Recommendation Networks: A Data-Centric Approach](https://mlsanity.com/paper/2206.02626/) (2022)
- [TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendations](https://mlsanity.com/paper/2203.10258/) (2022)
- [Respecting Transfer Gap in Knowledge Distillation](https://mlsanity.com/paper/2210.12787/) (2022)
- [A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction](https://mlsanity.com/paper/2211.06684/) (2022)
- [Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations](https://mlsanity.com/paper/2304.09085/) (2023)
- [Correcting Exposure Bias for Link Recommendation](https://mlsanity.com/paper/2106.07041/) (2021)

## Abstract (arXiv)

Most data for evaluating and training recommender systems is subject to selection biases, either through self-selection by the users or through the actions of the recommendation system itself. In this paper, we provide a principled approach to handling selection biases, adapting models and estimation techniques from causal inference. The approach leads to unbiased performance estimators despite biased data, and to a matrix factorization method that provides substantially improved prediction performance on real-world data. We theoretically and empirically characterize the robustness of the approach, finding that it is highly practical and scalable.