Lune

ICML2025Top-tier venue

Learning Classifiers That Induce Markets

Yonatan Sommer, Ivri Hikri, Lotan Amit, Nir Rosenfeld

Abstract

When learning is used to inform decisions about humans, such as for loans, hiring, or admissions, this can incentivize users to strategically modify their features, at a cost, to obtain positive predictions. The common assumption is that the function governing costs is exogenous, fixed, and predetermined. We challenge this assumption, and assert that costs emerge as a result of deploying a classifier. Our idea is simple: when users seek positive predictions, this creates demand for important features; and if features are available for purchase, then a market will form, and competition will give rise to prices. We extend the strategic classification framework to support this notion, and study learning in a setting where a classifier can induce a market for features. We present an analysis of the learning task, devise an algorithm for computing market prices, propose a differentiable learning framework, and conduct experiments to explore our novel setting and approach.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Ambiguous Strategic Classification cites Strategic Classification Made Practical
  • Ambiguous Strategic Classification cites Information Discrepancy in Strategic Learning
  • Ambiguous Strategic Classification cites Retiring Adult: New Datasets for Fair Machine Learning
  • Ambiguous Strategic Classification cites Strategic Classification in the Dark
  • Strategic Classification Made Practical cites Information Discrepancy in Strategic Learning
  • Strategic Classification Made Practical cites Strategic Classification in the Dark
  • Strategic Classification in the Dark cites Strategic Classification Made Practical
  • Welfare-Optimal Classification with Accuracy Auctions cites Strategic Classification Made Practical
  • Welfare-Optimal Classification with Accuracy Auctions cites Information Discrepancy in Strategic Learning
  • Welfare-Optimal Classification with Accuracy Auctions cites Retiring Adult: New Datasets for Fair Machine Learning
  • Information Discrepancy in Strategic Learning cites Strategic Classification in the Dark
  • Strategic Classification in the Dark cites Information Discrepancy in Strategic Learning
  • Robust Strategic Classification under Decision-Dependent Cost Uncertainty cites Information Discrepancy in Strategic Learning
  • Robust Strategic Classification under Decision-Dependent Cost Uncertainty cites Strategic Classification in the Dark
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Leaderboard Incentives: Model Rankings under Strategic Post-TrainingYatong Chen, Guanhua Zhang, Moritz HardtICML 2026 · 2 citations
  2. Ambiguous Strategic ClassificationIvri Hikri, Nir RosenfeldICML 2026
  3. Welfare-Optimal Classification with Accuracy AuctionsBana Sadi, Eden Saig, Nir RosenfeldICML 2026
  4. Robust Strategic Classification under Decision-Dependent Cost UncertaintySura Alhanouti, Guzin Bayraksan, Parinaz NaghizadehICML 2026

Builds on21

  1. Retiring Adult: New Datasets for Fair Machine LearningFrances Ding, Moritz Hardt, John Miller, Ludwig SchmidtNeurIPS 2021 · 671 citations
  2. SoftSort: A Continuous Relaxation for the argsort OperatorSebastian Prillo, Julian Martin EisenschlosICML 2020 · 94 citations
  3. Strategic Classification in the DarkGanesh Ghalme, Vineet Nair, Itay Eilat, Inbal Talgam-Cohen et al.ICML 2021 · 70 citations
  4. Strategic Classification Made PracticalSagi Levanon, Nir RosenfeldICML 2021 · 68 citations
  5. Information Discrepancy in Strategic LearningYahav Bechavod, Chara Podimata, Zhiwei Steven Wu, Juba ZianiICML 2022 · 57 citations

Related papers

  1. Classification Under Strategic Self-SelectionGuy Horowitz, Yonatan Sommer, Moran Koren, Nir RosenfeldICML 2024 · 8 citations
  2. Strategic Classification with Graph Neural NetworksItay Eilat, Ben Finkelshtein, Chaim Baskin, Nir RosenfeldICLR 2023
  3. Generalized Strategic Classification and the Case of Aligned IncentivesSagi Levanon, Nir RosenfeldICML 2022 · 30 citations
  4. Strategic Classification with Non-Linear ClassifiersBenyamin Trachtenberg, Nir RosenfeldNeurIPS 2025 · 5 citations
  5. Desirable Effort Fairness and Optimality Trade-offs in Strategic LearningValia Efthymiou, Ekaterina Fedorova, Chara PodimataICML 2026 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines