# Manipulation-Proof Machine Learning

arXiv: https://arxiv.org/abs/2004.03865 · HTML: https://mlsanity.com/paper/2004.03865/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 20 of 20)

- [How to Learn when Data Reacts to Your Model: Performative Gradient Descent](https://mlsanity.com/paper/2102.07698/) (2021)
- [Information Discrepancy in Strategic Learning](https://mlsanity.com/paper/2103.01028/) (2021)
- [Alternative Microfoundations for Strategic Classification](https://mlsanity.com/paper/2106.12705/) (2021)
- [Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse](https://mlsanity.com/paper/2203.06768/) (2022)
- [Anticipating Performativity by Predicting from Predictions](https://mlsanity.com/paper/2208.07331/) (2022)
- [Bayesian Strategic Classification](https://mlsanity.com/paper/2402.08758/) (2024)
- [Accounting for AI and Users Shaping One Another: The Role of Mathematical Models](https://mlsanity.com/paper/2404.12366/) (2024)
- [Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes](https://mlsanity.com/paper/2307.05862/) (2023)
- [Unfairness Despite Awareness: Group-Fair Classification with Strategic Agents](https://mlsanity.com/paper/2112.02746/) (2021)
- [Sequential Strategic Screening](https://mlsanity.com/paper/2301.13397/) (2023)
- [Who's Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation](https://mlsanity.com/paper/2412.02000/) (2024)
- [Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality](https://mlsanity.com/paper/2505.05211/) (2025)
- [Practical Performative Policy Learning with Strategic Agents](https://mlsanity.com/paper/2412.01344/) (2024)
- [Policy Learning with Competing Agents](https://mlsanity.com/paper/2204.01884/) (2022)
- [Incentives to Offer Algorithmic Recourse](https://mlsanity.com/paper/2301.12884/) (2023)
- [Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse](https://mlsanity.com/paper/2410.02273/) (2024)
- [Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmap](https://mlsanity.com/paper/2502.11981/) (2025)
- [Program Targeting with Machine Learning and Mobile Phone Data: Evidence from an Anti-Poverty Intervention in Afghanistan](https://mlsanity.com/paper/2206.11400/) (2022)
- [Performance Manipulation: Labor Market Implications in AI-assisted Era](https://mlsanity.com/paper/2604.22230/) (2026)
- [Robust Strategic Classification under Decision-Dependent Cost Uncertainty](https://mlsanity.com/paper/2606.30136/) (2026)

## Abstract (arXiv)

An increasing number of decisions are guided by machine learning algorithms. In many settings, from consumer credit to criminal justice, those decisions are made by applying an estimator to data on an individual's observed behavior. But when consequential decisions are encoded in rules, individuals may strategically alter their behavior to achieve desired outcomes. This paper develops a new class of estimator that is stable under manipulation, even when the decision rule is fully transparent. We explicitly model the costs of manipulating different behaviors, and identify decision rules that are stable in equilibrium. Through a large field experiment in Kenya, we show that decision rules estimated with our strategy-robust method outperform those based on standard supervised learning approaches.