Recalibrating selection algorithms prevents automated systems from reproducing past discrimination patterns.

Download image · 1200 × 630 PNG

Try, learn and adjust

Check diversity in recruitment recommendations

  1. Plan: Audit the recruitment algorithm for bias affecting applicants such as Meena.
  2. Try: Adjust selection parameters for historical discrimination and deploy the revised screening.
  3. Learn: Check demographic selection rates and overall hiring levels.
  4. Adjust: Keep monitoring both measures next cycle; change parameters if observed selection patterns still show bias.

Illustrative: Meena is fictional. School’s suggested learning loop, not the source study’s tested protocol.

See source →

School’s suggested, untested loop. Observe demographic selection rates and overall hiring; do not assume recalibration removes bias.

How

When to use

Standard automated recruitment algorithms trained on historical hiring data often reproduce past discrimination, selecting far fewer minority candidates. Employers want to maintain high hiring efficiency without worsening demographic disparities. Re-engineering recruitment algorithms allows digital platforms to evaluate applicants fairly while selecting a diverse pool of qualified candidates.

Adjust automated recruitment algorithms to explicitly optimize for candidate diversity while evaluating applicant qualifications.

  1. Platform engineers audit existing screening algorithms for demographic bias in candidate recommendations.
  2. Data scientists modify the algorithm selection parameters to account for historical discrimination patterns.
  3. The platform deploys the recalibrated algorithm to screen applicant resumes for employers.
  4. Hiring managers review candidate recommendation pools featuring greater demographic representation.
  5. Program officers track candidate selection rates and overall hiring levels.

Why it works

This allows platforms to identify qualified candidates from underrepresented groups without reducing hiring efficiency.

Example

In an evaluation of hiring algorithms, researchers found that initial algorithms selected far fewer Black and Hispanic candidates, but using a recalibrated algorithm increased demographic diversity while keeping hiring rates high.

Source

See source →

Filipe Cavalcanti; Laísa Ratcher; Livia Gouvêa; Luiz Felipe Fontes

Evidence in Labor Market Policies and Implications for Brazil: Job Search Assistance

CC BY 3.0 IGO

Full source notice

Copyright © 2023 Inter-American Development Bank ("IDB"). This work is subject to a Creative Commons license CC BY 3.0 IGO (https://creativecommons.org/licenses/by/3.0/igo/legalcode). The terms and conditions indicated in the URL link must be met and the respective recognition must be granted to the IDB. Further to section 8 of the above license, any mediation relating to disputes arising under such license shall be conducted in accordance with the WIPO Mediation Rules. Any dispute related to the use of the works of the IDB that cannot be settled amicably shall be submitted to arbitration pursuant to the United Nations Commission on International Trade Law (UNCITRAL) rules. The use of the IDB's name for any purpose other than for attribution, and the use of IDB's logo shall be subject to a separate written license agreement between the IDB and the user and is not authorized as part of this license. Note that the URL link includes terms and conditions that are an integral part of this license.