The Effects of Algorithmic Labor Market Recommendations: Evidence from a Field Experiment

Algorithmically recommending workers to employers for the purpose of recruiting can substantially increase hiring: in an experiment conducted in an online labor market, employers with technical job vacancies that received recruiting recommendations had a 20% higher fill rate compared to the control. There is no evidence that the treatment crowded out hiring of nonrecommended candidates. The experimentally induced recruits were highly positively selected and were statistically indistinguishable from the kinds of workers employers recruit “on their own.” Recommendations were most effective for job openings that were likely to receive a smaller applicant pool.

[1]  P. Gautier,et al.  Estimating Equilibrium Effects of Job Search Assistance , 2012, Journal of Labor Economics.

[2]  J. Horton,et al.  Price Floors and Employer Preferences: Evidence from a Minimum Wage Experiment , 2017, SSRN Electronic Journal.

[3]  M. Hoffman,et al.  Discretion in Hiring , 2015 .

[4]  Ramesh Johari,et al.  At What Quality and What Price?: Eliciting Buyer Preferences as a Market Design Problem , 2015, EC.

[5]  Elizabeth Lyons,et al.  Digitization and the Contract Labor Market: A Research Agenda , 2013 .

[6]  Amanda Pallais.  Ineffiient Hiring in Entry-Level Labor Markets , 2012 .

[7]  Elizabeth Lyons,et al.  Does Information Help or Hinder Job Applicants from Less Developed Countries in Online Markets? , 2013 .

[8]  Christopher T. Stanton,et al.  Landing the First Job: The Value of Intermediaries in Online Hiring , 2014 .

[9]  Esther Duflo,et al.  Do Labor Market Policies Have Displacement Effects? Evidence from a Clustered Randomized Experiment , 2012 .

[10]  P. Kuhn,et al.  Is Internet Job Search Still Ineffective? , 2014, SSRN Electronic Journal.

[11]  Jochen Kluve.  The effectiveness of European active labor market programs , 2010 .

[12]  Scott Schaefer,et al.  Personnel Economics: Hiring and Incentives , 2010 .

[13]  H. Varian.  Computer Mediated Transactions , 2010 .

[14]  David H. Autor,et al.  Does Job Testing Harm Minority Workers? Evidence from Retail Establishments , 2008 .

[15]  M. Pellizzari.  Employers' Search and the Efficiency of Matching , 2005, SSRN Electronic Journal.

[16]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[17]  Peter Kuhn,et al.  Internet Job Search and Unemployment Durations , 2002, SSRN Electronic Journal.

[18]  K. Burdett,et al.  Toward a Theory of Vacancies , 1998, Journal of Labor Economics.

[19]  Paul Resnick,et al.  Recommender systems , 1997, CACM.

[20]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[21]  G. Ridder,et al.  Vacancies and the Recruitment of New Employees , 1992, Journal of Labor Economics.

[22]  John M. Barron,et al.  Job Matching and On-the-Job Training , 1989, Journal of Labor Economics.

[23]  John M. Barron,et al.  EXTENSIVE SEARCH, INTENSIVE SEARCH, AND HIRING COSTS: NEW EVIDENCE ON EMPLOYER HIRING ACTIVITY , 1985 .