Using AI to Expand the Job Search of Displaced Workers in the Aftermath of the Covid-19 Crisis

How to cite

Gauthier, Jean-Francois; Tamayo, Jorge; Nyshadham, Anant; Adhvaryu, Achyuta. 2021. "Using AI to Expand the Job Search of Displaced Workers in the Aftermath of the Covid-19 Crisis." AEA RCT Registry. AEARCTR-0007099. https://doi.org/10.1257/rct.7099-1.0

Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.

Jean-Francois Gauthier* , Jorge Tamayo , Anant Nyshadham , Achyuta Adhvaryu

* Primary investigator

Registry ID
AEARCTR-0007099
DOI
https://doi.org/10.1257/rct.7099-1.0
First registered
Last updated
Status
In development
Trial dates
2021-04-01 – 2022-01-01
Countries
Private
Registry record
http://www.socialscienceregistry.org/trials/7099

Abstract

To date, more than 38 million workers have filed for unemployment during the COVID-19 crisis. Early evidence suggests that the worst economic impacts will be concentrated among entry-level service workers, who are disproportionately young, female, and from marginalized groups. These populations are often slow to be reintegrated into the economy after economic contractions due at least in part to discrimination and imperfect information, with full recovery from the last decade’s financial crisis, for example, taking more than 7 years.
This inequality in employment outcomes is caused in part by job search frictions that disproportionately affect the ability of low-income minority workers to find good matches. In the proposed study, we investigate whether AI-assisted algorithmic matching of skills and psychometric profiles to overlooked vacancies can help displaced workers from entry-level service occupations in their search for employment. To do so, we propose a large-scale randomized controlled trial (RCT) in the United States building on our prior work that focuses on workers who were displaced from their prior jobs as a result of the COVID-19 pandemic.
The RCT will: 1) Use trained machine learning algorithms from prior experiments to predict job performance across a broad array of recovering occupations from psychometric profiles of job seekers; 2) Share a combination of information on best matched occupations and real vacancies,
highlighting deviations from prior search experience.
We will recruit job seekers from online job portals to complete the psychometric survey and answer questions about demographics, recent work, and job search history (including if they have been recently laid off due to Covid-19). After randomized assignment to one of several experimental groups, we will track employment status, job search success rates, time to reemployment, and compensation.

Experimental design

Participants will be randomized to receive a list of local vacancies according to the treatment arm in which they are allocated. Participants in the control group will see a random list of URLs linking to locally available job vacancies. In the first treatment arm we reduce the respondents’ search cost. In the second treatment arm, participants receive the same local list of randomly sorted vacancies as the control group, but we provide information to participants about the entry-level occupations that we predict may be a good fit for them. In the last treatment arm, we reduce both search cost and provide occupational fit information.

Design details

Randomization method
Randomization done in office by a computer
Randomization unit
Individuals
Clusters
1,640 adults
Observations
1,640 adults
Arms
410 adults per arm
Primary outcomes
Hazard of reemployment, employment status, hours spent searching for job openings, number of searches, number of applications, number of call backs, number of interviews, number of offers, offer satisfaction, yearly earnings.

Cited by

No citation data available for this registration yet.

Keywords