How Do Classifiers Induce Agents To Invest Effort Strategically?

TL;DR

This paper models how strategic agents decide to invest effort to influence classification outcomes and identifies conditions under which simple linear mechanisms effectively incentivize desired effort levels.

Contribution

It provides a theoretical framework characterizing when and how classifiers can incentivize agents to invest effort, highlighting the sufficiency of linear mechanisms.

Findings

Linear mechanisms can incentivize effort when certain conditions are met.

A tight characterization of effort inducement versus gaming strategies.

Simple mechanisms are often sufficient for strategic effort incentives.

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.