Classification with Strategically Withheld Data

TL;DR

This paper addresses the challenge of strategic feature withholding in classification tasks, proposing three robust methods ({ extsc{Mincut}, { extsc{HC}}, and { extsc{IC-LR}}) to prevent incentives for hiding data and improve classifier robustness.

Contribution

The paper introduces novel classification algorithms that are incentive-compatible, effectively preventing strategic feature withholding and enhancing robustness against such behavior.

Findings

{ extsc{Mincut} is optimal with known data distribution}

{ extsc{HC} is a simpler, convergent hierarchical ensemble}

{ extsc{IC-LR} removes incentives to hide features}

Abstract

Machine learning techniques can be useful in applications such as credit approval and college admission. However, to be classified more favorably in such contexts, an agent may decide to strategically withhold some of her features, such as bad test scores. This is a missing data problem with a twist: which data is missing {\em depends on the chosen classifier}, because the specific classifier is what may create the incentive to withhold certain feature values. We address the problem of training classifiers that are robust to this behavior. We design three classification methods: {\sc Mincut}, {\sc Hill-Climbing} ({\sc HC}) and Incentive-Compatible Logistic Regression ({\sc IC-LR}). We show that {\sc Mincut} is optimal when the true distribution of data is fully known. However, it can produce complex decision boundaries, and hence be prone to overfitting in some cases. Based on a characterization of truthful classifiers (i.e., those that give no incentive to strategically hide features), we devise a simpler alternative called {\sc HC} which consists of a hierarchical ensemble of out-of-the-box classifiers, trained using a specialized hill-climbing procedure which we show to be convergent. For several reasons, {\sc Mincut} and {\sc HC} are not effective in utilizing a large number of complementarily informative features. To this end, we present {\sc IC-LR}, a modification of Logistic Regression that removes the incentive to strategically drop features. We also show that our algorithms perform well in experiments on real-world data sets, and present insights into their relative performance in different settings.