Title: Optimising of support plans for new graduate employment market using reinforcement learning

Authors: Keiko Mori, Setsuya Kurahashi

Addresses: Graduate School of Business Sciences, University of Tsukuba, 3-29-1 Otsuka Bunkyo-ku, Tokyo, 112-0012, Japan. ' Graduate School of Business Sciences, University of Tsukuba, 3-29-1 Otsuka Bunkyo-ku, Tokyo, 112-0012, Japan

Abstract: We focus on the job matching processes in the market for new graduates in Japan, where students and companies select each other. This job matching process does not always function effectively. We conducted an agent-based simulation with reinforcement learning in order to confirm the phenomenon in the market. We adopted two types of reinforcement learning: the Profit Sharing method and the Actor-Critic method. After some experiments, it was found that both methods effectively support students| job-hunting activities and raise the finding-employment proportion of the entire graduate employment market.

Keywords: agent-based simulation; job matching process; reinforcement learning; mulit-agent systems; agent-based systems; Japan; new graduates; university graduates; job market; graduate employment; finding employment.

DOI: 10.1504/IJCAT.2011.041654

International Journal of Computer Applications in Technology, 2011 Vol.40 No.4, pp.254 - 264

Published online: 28 Jul 2011 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article