Predicting job match quality: A machine learning approach

This paper develops a large-scale algorithm‑based application to improve the match quality in the labor market. We use comprehensive administrative data on employment biographies in Germany to predict job match quality in terms of job stability and wages. The models are estimated with both machine learning (ML) (i.e., XGBoost) and common statistical methods (i.e., OLS, logit). Compared to the latter approach, we find that XGBoost performs better for pattern recognition, analyzes large amounts of data in an efficient way and minimizes the prediction error in the application. Finally, we combine our results with algorithms that optimize matching probability to provide a ranked list of job recommendations based on individual characteristics for each job seeker. This application could support caseworkers and job seekers in expanding their job search strategy.