How Do Classifiers Induce Agents to Invest Effort Strategically?
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Algorithms are often used to produce decision-making rules that classify or evaluate individuals. When these individuals have incentives to be classified a certain way, they may behave strategically to influence their outcomes. We develop a model for how strategic agents can invest effort in order to change the outcomes they receive, and we give a tight characterization of when such agents can be incentivized to invest specified forms of effort into improving their outcomes as opposed to "gaming" the classifier. We show that whenever any "reasonable" mechanism can do so, a simple linear mechanism suffices.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Spence, M. (1973) · The Quarterly Journal of Economics · doi:10.2307/1882010 · Cited by 19,518
Multitask principal – agent analyses: Incentive contracts, asset ownership, and job design
Holmstrom, B., & Milgrom, P. (1991) · The Journal of Law, Economics, and Organization · doi:10.1093/jleo/7.special_issue.24 · Cited by 6,046
Managerial Incentive Problems: A Dynamic Perspective
Holmstrom, B. (1999) · Review of Economic Studies · doi:10.1111/1467-937x.00083 · Cited by 3,172
On the folly of rewarding A, while hoping for B
Kerr, S. (1975) · Academy of Management Journal · doi:10.2307/255378 · Cited by 1,585
Stackelberg games for adversarial prediction problems
Brückner, M., & Scheffer, T. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020495 · Cited by 229 · cited 1×
“in the case of spam detection, and more recently in terms of Stackelberg competitions, in which the evaluator publishes a rule and the agent may respond by manipulating their features strategically [5, 13, 18, 23, 29].”
BackgroundDutton, W. H., & Kraemer, K. L. (1980) · Society · doi:10.1007/bf02700058 · Cited by 20
Cited by
Actionable Recourse in Linear Classification
Ustun, B., Spangher, A., & Liu, Y. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287566 · Cited by 501
Inherent Tradeoffs in the Fair Determination of Risk Scores
(2023) · The Societal Impacts of Algorithmic Decision-Making · doi:10.1145/3603195.3603197 · Cited by 310
A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
Karimi, A.-H., Barthe, G., Schölkopf, B., & Valera, I. (2023) · ACM Computing Surveys · doi:10.1145/3527848 · Cited by 301
Bayamlıoğlu, E. (2022) · Regulation & Governance · doi:10.1111/rego.12391 · Cited by 44
Forks over knives: Predictive inconsistency in criminal justice algorithmic risk assessment tools
Greene, T., Shmueli, G., Fell, J., Lin, C.-F., & Liu, H.-W. (2022) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/rssa.12966 · Cited by 15
Metadata
- Authors
- Kleinberg, J., & Raghavan, M.
- Venue
- Proceedings of the 2019 ACM Conference on Economics and Computation
- Publisher
- ACM
- Published
- 2019-06-17
- Volume
- 8
- Issue
- 4
- Pages
- 825-844
- OpenAlex
- W2884171929
- Cited by
- 105
- References
- 6
- FWCI
- 56.54
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.