Estimating Misreporting in the Presence of Genuine Modification: A Causal Perspective

TL;DR

This paper introduces a causal method to distinguish and quantify agent misreporting from genuine feature modifications in ML-driven resource allocation, addressing a key challenge in strategic behavior analysis.

Contribution

It proposes a causally-motivated approach that identifies misreporting by exploiting the causal asymmetry between deceptive and genuine feature changes, with formal proofs and empirical validation.

Findings

Successfully distinguishes misreporting from genuine modification in datasets

Provides a formal proof of identifiability of misreporting rate

Validated approach on semi-synthetic and real Medicare data

Abstract

In settings where ML models are used to inform the allocation of resources, agents affected by the allocation decisions might have an incentive to strategically change their features to secure better outcomes. While prior work has studied strategic responses broadly, disentangling misreporting from genuine modification remains a fundamental challenge. In this paper, we propose a causally-motivated approach to identify and quantify how much an agent misreports on average by distinguishing deceptive changes in their features from genuine modification. Our key insight is that, unlike genuine modification, misreported features do not causally affect downstream variables (i.e., causal descendants). We exploit this asymmetry by comparing the causal effect of misreported features on their causal descendants as derived from manipulated datasets against those from unmanipulated datasets. We formally prove identifiability of the misreporting rate and characterize the variance of our estimator. We empirically validate our theoretical results using a semi-synthetic and real Medicare dataset with misreported data, demonstrating that our approach can be employed to identify misreporting in real-world scenarios.