A0303
Title: Predicting job match quality: A machine learning approach
Authors: Sabrina Muehlbauer - Institute for Employment Research (Germany) [presenting]
Abstract: A large-scale algorithm-based application is developed to improve the match quality in the labor market. Large administrative data is used on employment biographies in Germany to predict job match quality in terms of job stability and wages. The models are estimated with machine learning (ML) (i.e., XGBoost) and common statistical methods (i.e., OLS, logit). Compared to the latter, it is found that XGBoost performs better for pattern recognition, dealing with large data, and minimizing the prediction error in this application. Finally, the results are combined with algorithms optimizing matching probability for providing a ranked list of job recommendations based on individual characteristics for each job seeker. This could support caseworkers and job seekers to enlarge the job search strategy.
