Hiring as Exploration.

This article views hiring as a contextual bandit problem: to find the best workers over time, firms must balance "exploitation" (selecting from groups with proven track records) with "exploration" (selecting from under-represented groups to learn about quality). Yet modern hiring algorithms, based o...

Descripción completa

Detalles Bibliográficos
Publicado en:Review of Economic Studies Vol. 93; no. 2; pp. 1200 - 1241
Autores principales: Li, Danielle, Raymond, Lindsey, Bergman, Peter
Formato: Artículo
Publicado: Oxford University Press / USA Mar2026
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=192334031&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 192334031
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00346527
        REM
      jtl: Review of Economic Studies
      issn: 00346527
      maglogo: N
    pubinfo:
      dt: Mar2026
      vid: 93
      iid: 2
      pid: 622
      pub: Oxford University Press / USA
    artinfo:
      ui:
        192334031
        10.1093/restud/rdaf040
      ppf: 1200
      ppct: 41
      formats:
      tig:
        atl: Hiring as Exploration.
      aug:
        au:
          Li, Danielle
          Raymond, Lindsey
          Bergman, Peter
        affil:
          Massachusetts Institute of Technology and National Bureau of Economic Research, USA
          Massachusetts Institute of Technology, USA
          The University of Texas at Austin and National Bureau of Economic Research, USA
      su:
        Decision making
        Employee recruitment
        Algorithms
        Job resumes
        Supervised learning
      sug:
        subj:
          Decision making
          Administration of Human Resource Programs (except Education, Public Health, and Veterans' Affairs Programs)
          Human Resources Consulting Services
          Employee recruitment
          Algorithms
          Job resumes
          Supervised learning
      keyword:
        Algorithmic fairness
        Contextual bandits
        copyrightHolder:Review of Economic Studies Ltd
        copyrightYear:2026
        Hiring
        inLanguage:en
        Job search
        Machine learning
        publisher:Oxford University Press
        sameAs:https://dx.doi.org/10.1093/restud/rdaf040
        Algorithmic fairness
        Contextual bandits
        copyrightHolder:Review of Economic Studies Ltd
        copyrightYear:2026
        Hiring
        inLanguage:en
        Job search
        Machine learning
        publisher:Oxford University Press
        sameAs:https://dx.doi.org/10.1093/restud/rdaf040
      ab: This article views hiring as a contextual bandit problem: to find the best workers over time, firms must balance "exploitation" (selecting from groups with proven track records) with "exploration" (selecting from under-represented groups to learn about quality). Yet modern hiring algorithms, based on supervised learning approaches, are designed solely for exploitation. Instead, we build a resume screening algorithm that values exploration by evaluating candidates according to their statistical upside potential. Using data from professional services recruiting within a Fortune 500 firm, we show that this approach improves the quality (as measured by eventual hiring rates) of candidates selected for an interview, while also increasing demographic diversity, relative to the firm's existing practices. The same is not true for traditional supervised learning-based algorithms, which improve hiring rates but select far fewer Black and Hispanic applicants. Together, our results highlight the importance of incorporating exploration in developing decision-making algorithms that are potentially both more efficient and equitable.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N