How Do Classifiers Induce Agents to Invest Effort Strategically?

By Jon M. Kleinberg, Manish Raghavan. 2018

167 citations recorded by the source corpus.

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.

Subfields: Management Science and Operations Research, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Safety Research

Citations in the corpus

Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “Alternatively, dynamics can be considered in a way that is socially beneficial [57, 75].”
Optimal Decision Making Under Strategic Behavior (2019, background): “…strategic effort as some form of gaming, and thus undesirable—an individual’s effort in changing their features may actually lead sometimes to self-improvement, as noted by several studies in the economic literature [3, 7, 10] and, more recently, in the theoretical computer science literature [14].”
The Social Cost of Strategic Classification (2018, background): “Kleinberg and Raghavan [19] studies how to design classifiers that produce such incentives.”
The hidden assumptions behind counterfactual explanations and principal reasons (2019, unknown): “But there are often many other ways to change feature values that don’t require taking these steps [22].”
Performative Prediction (2020, background): “Recent work in this area considers issues of incentive design [23, 27], control over an algorithm [7], and fairness concerns [17, 28].”