Algorithmic Decision-Making under Agents with Persistent Improvement

TL;DR

This paper models strategic human behavior in algorithmic decision-making, focusing on persistent effort improvements and how decision-makers can incentivize optimal, honest efforts in dynamic, potentially dishonest environments.

Contribution

It introduces a dynamic model with persistent improvements, analyzes equilibrium strategies, and designs optimal policies to incentivize honest, sustained efforts in strategic agents.

Findings

Agents have incentives to improve under certain conditions.

Optimal policies can incentivize maximum improvements.

Honest efforts are favored when incentives are properly aligned.

Abstract

This paper studies algorithmic decision-making under human's strategic behavior, where a decision maker uses an algorithm to make decisions about human agents, and the latter with information about the algorithm may exert effort strategically and improve to receive favorable decisions. Unlike prior works that assume agents benefit from their efforts immediately, we consider realistic scenarios where the impacts of these efforts are persistent and agents benefit from efforts by making improvements gradually. We first develop a dynamic model to characterize persistent improvements and based on this construct a Stackelberg game to model the interplay between agents and the decision-maker. We analytically characterize the equilibrium strategies and identify conditions under which agents have incentives to improve. With the dynamics, we then study how the decision-maker can design an optimal policy to incentivize the largest improvements inside the agent population. We also extend the model to settings where 1) agents may be dishonest and game the algorithm into making favorable but erroneous decisions; 2) honest efforts are forgettable and not sufficient to guarantee persistent improvements. With the extended models, we further examine conditions under which agents prefer honest efforts over dishonest behavior and the impacts of forgettable efforts.