Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics

TL;DR

This paper introduces a multi-level promotion-relegation framework for strategic classification, focusing on threshold design to incentivize honest effort and enable agents to achieve high levels through genuine improvement.

Contribution

It departs from weight-centric models by analyzing threshold and difficulty progression, demonstrating how to design incentives for long-term honest effort in strategic classification.

Findings

Mechanism allows agents to reach arbitrarily high levels through genuine effort.

Threshold design effectively incentivizes honest behavior over time.

Agents' long-term strategies are characterized under the proposed framework.

Abstract

Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly than genuine efforts. While existing studies on sequential strategic classification primarily focus on optimizing dynamic classifier weights, we depart from these weight-centric approaches by analyzing the design of classifier thresholds and difficulty progression within a multi-level promotion-relegation framework. Our model captures the critical inter-temporal incentives driven by an agent's farsightedness, skill retention, and a leg-up effect where qualification and attainment can be self-reinforcing. We characterize the agent's optimal long-term strategy and demonstrate that a principal can design a sequence of thresholds to effectively incentivize honest effort. Crucially, we prove that under mild conditions, this mechanism enables agents to reach arbitrarily high levels solely through genuine improvement efforts.