American Economic Review
ISSN 0002-8282 (Print) | ISSN 1944-7981 (Online)
Manipulation-Robust Prediction
American Economic Review
(pp. 3263–93)
Abstract
An increasing number of decisions are guided by machine learning algorithms. But when consequential decisions are encoded in algorithms, individuals may strategically alter their behavior to achieve desired outcomes. This paper develops an empirical approach that adjusts decision algorithms to anticipate manipulation. By explicitly modeling incentives to manipulate, our approach produces decision rules that are stable under manipulation, even when the rules are fully transparent. We stress-test this approach through a large field experiment in Kenya. When implemented, linear strategy-robust decision rules outperform standard linear models such as LASSO.Citation
Björkegren, Daniel, Joshua E. Blumenstock, and Samsun Knight. 2026. "Manipulation-Robust Prediction." American Economic Review 116 (9): 3263–93. DOI: 10.1257/aer.20241087Additional Materials
JEL Classification
- C45 Neural Networks and Related Topics
- C93 Field Experiments
- D12 Consumer Economics: Empirical Analysis
- D91 Micro-Based Behavioral Economics: Role and Effects of Psychological, Emotional, Social, and Cognitive Factors on Decision Making
- G51 Household Finance: Household Saving, Borrowing, Debt, and Wealth
- O12 Microeconomic Analyses of Economic Development
- O16 Economic Development: Financial Markets; Saving and Capital Investment; Corporate Finance and Governance