How can AI improve search and matching? Evidence from 59 million personalized job recommendations

Abstract

We explore how artificial intelligence can be leveraged to help frictional markets to clear. We design a job recommender system that uses job seekers' history of job ad views to generate relevant personalized job recommendations. We deploy it at scale on the largest online job board in Sweden. We design a clustered two-sided randomized experiment to evaluate its impact on job search and labor-market outcomes. First, at the labor market level, the recommender system increases employment by 0.4% within a few months. Second, at the worker-level, treated job seekers are more likely to apply to recommended vacancies, at the expense of non-recommended ones: the total number of applications remains unchanged. Treated unemployed job seekers have 0.8% higher employment with no significant effects on match quality, while we do not find any employment effects for job seekers employed at randomization. Third, we study the heterogeneity of the employment effect at the job seeker-vacancy level and we find that workers with lower employment prospects and jobs attracting less attention are those benefitting the most from the recommender system. This suggests that the increase in matching efficiency is paired with a reduction in inequality.