Strategic Classification
Moritz Hardt, Nimrod Megiddo, Christos Papadimitriou, Mary Wootters

TL;DR
This paper addresses the challenge of creating machine learning classifiers that remain accurate when individuals strategically manipulate their attributes to game the system, proposing game-theoretic models and algorithms for robustness.
Contribution
It formalizes the problem of strategic classification, introduces a game-theoretic framework, and develops efficient algorithms for near-optimal, robust classifiers under certain cost functions.
Findings
Efficient algorithms for near-optimal strategic classifiers with specific cost functions.
Robust classifiers maintain accuracy despite strategic manipulation.
NP-hardness results for general cost functions.
Abstract
Machine learning relies on the assumption that unseen test instances of a classification problem follow the same distribution as observed training data. However, this principle can break down when machine learning is used to make important decisions about the welfare (employment, education, health) of strategic individuals. Knowing information about the classifier, such individuals may manipulate their attributes in order to obtain a better classification outcome. As a result of this behavior---often referred to as gaming---the performance of the classifier may deteriorate sharply. Indeed, gaming is a well-known obstacle for using machine learning methods in practice; in financial policy-making, the problem is widely known as Goodhart's law. In this paper, we formalize the problem, and pursue algorithms for learning classifiers that are robust to gaming. We model classification as a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Advanced Bandit Algorithms Research · Auction Theory and Applications
