How Do Classifiers Induce Agents To Invest Effort Strategically?
This addresses the issue of strategic manipulation in algorithmic decision-making, which is a problem for designers of fair and effective classification systems, and it provides a foundational theoretical result.
The paper tackles the problem of strategic agents gaming classifiers by developing a model that characterizes when agents can be incentivized to invest effort into improving outcomes rather than gaming, showing that a simple linear mechanism suffices whenever any reasonable mechanism can achieve this.
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.