Maximizing Welfare with Incentive-Aware Evaluation Mechanisms
read the original abstract
Motivated by applications such as college admission and insurance rate determination, we propose an evaluation problem where the inputs are controlled by strategic individuals who can modify their features at a cost. A learner can only partially observe the features, and aims to classify individuals with respect to a quality score. The goal is to design an evaluation mechanism that maximizes the overall quality score, i.e., welfare, in the population, taking any strategic updating into account. We further study the algorithmic aspect of finding the welfare maximizing evaluation mechanism under two specific settings in our model. When scores are linear and mechanisms use linear scoring rules on the observable features, we show that the optimal evaluation mechanism is an appropriate projection of the quality score. When mechanisms must use linear thresholds, we design a polynomial time algorithm with a (1/4)-approximation guarantee when the underlying feature distribution is sufficiently smooth and admits an oracle for finding dense regions. We extend our results to settings where the prior distribution is unknown and must be learned from samples.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Linear Strategic Classification with Endogenous Improvements
Formalizes improvement-aware strategic classification for linear classifiers under single-index models, proves the strategic-optimal classifier is a parallel shift of the Bayes boundary, and supplies PAC guarantees wi...
-
Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
Defines behaviorally realistic strategic classification and proposes Pro-SF framework grounded in prospect theory to model biased agent manipulations in Stackelberg interactions.
-
Sequential Strategic Classification with Multi-Stage Selective Classifiers
A new multi-stage sequential model with selective classifiers is proposed to characterize agent actions and design sequences that incentivize genuine improvement rather than gaming in strategic classification.
-
Beyond Independent Manipulation: Individual Fairness-aware Strategic Classification with Peer Imitation
Introduces IFSC framework modeling peer imitation in individual fairness-aware strategic classification to improve fairness consistency under interdependent manipulations.
-
Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
Defines behaviorally realistic strategic classification and proposes Pro-SF, a prospect-theory-based framework to model non-rational agent manipulations in strategic classification.
-
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
The paper proposes Strategic Prior-data Fitted Network (SPN), an inference-time framework that adapts pretrained tabular foundation models (PFNs) to strategic manipulation by aligning predictions with approximated pos...
-
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
The paper proposes Strategic Prior-data Fitted Network (SPN), an inference-time method that adapts pretrained tabular foundation models to strategic feature manipulation by constructing aligned in-context examples.
-
Partial Fairness Awareness: Belief-Guided Strategic Mechanism for Strategic Agents
Introduces partial fairness awareness (PFA) and a belief-guided mechanism allowing strategic agents to align beliefs with a hidden grounding fairness constraint via iterative interaction.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.