Efficient candidate screening under multiple tests and implications for fairness

Lee Cohen, Zachary C. Lipton, Yishay Mansour

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

When recruiting job candidates, employers rarely observe their underlying skill level directly. Instead, they must administer a series of interviews and/or collate other noisy signals in order to estimate the worker’s skill. Traditional economics papers address screening models where employers access worker skill via a single noisy signal. In this paper, we extend this theoretical analysis to a multi-test setting, considering both Bernoulli and Gaussian models. We analyze the optimal employer policy both when the employer sets a fixed number of tests per candidate and when the employer can set a dynamic policy, assigning further tests adaptively based on results from the previous tests. To start, we characterize the optimal policy when employees constitute a single group, demonstrating some interesting trade-offs. Subsequently, we address the multi-group setting, demonstrating that when the noise levels vary across groups, a fundamental impossibility emerges whereby we cannot administer the same number of tests, subject candidates to the same decision rule, and yet realize the same outcomes in both groups. We show that by subjecting members of noisier groups to more tests, we can equalize the confusion matrix entries across groups, seemingly eliminating any disparate impact concerning outcomes.

Original languageEnglish
Title of host publication1st Symposium on Foundations of Responsible Computing, FORC 2020
EditorsAaron Roth
PublisherSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
ISBN (Electronic)9783959771429
DOIs
StatePublished - 1 May 2020
Event1st Symposium on Foundations of Responsible Computing, FORC 2020 - Virtual, Cambridge, United States
Duration: 1 Jun 2020 → …

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
Volume156
ISSN (Print)1868-8969

Conference

Conference1st Symposium on Foundations of Responsible Computing, FORC 2020
Country/TerritoryUnited States
CityVirtual, Cambridge
Period1/06/20 → …

Funding

FundersFunder number
Yandex Initiative for Machine Learning
Israel Science Foundation

    Keywords

    • Algorithmic fairness
    • Inference
    • Random walk

    Fingerprint

    Dive into the research topics of 'Efficient candidate screening under multiple tests and implications for fairness'. Together they form a unique fingerprint.

    Cite this