Nonparametric Estimation of Matching Efficiency and Elasticity on a Private On-the-Job Search Platform: Evidence from Japan, 2014-2024

Abstract: I use proprietary data from the online job scouting platform BizReach in Japan, spanning from 2014 to 2024, to estimate the matching function for high-skill employed workers on a private on-the-job search platform, employing a novel nonparametric approach developed by Lange and Papageorgiou (2020). This analysis is compared to the public off-the-job search platform, Hello Work. The results indicate that matching efficiency on the private platform is both more volatile and higher than that of the public platform, suggesting the increasing popularity of the private platform. The matching elasticity with respect to users consistently hovers around 0.75, while the elasticity with respect to vacancies reaches approximately 1.0, indicating a higher and more balanced elasticity compared to the Hello Work platform. Additionally, the study reveals evidence of industry-level heterogeneity on the private platform.