Michael Mark Wins INFORMS Best Student Paper Competition
At the 2020 INFORMS Annual Meeting, Michael Mark, a PhD Student at the Chair of Operations, Economics and Strategy, was invited to the finals of the Best Student Paper Award in Finance. With the presentation of his paper, “A Reinforcement-Learning Approach to Credit Collections,” he impressed a jury composed of industry experts and faculty, emerging as the only winner in the strong field of this year’s competition. A honorable mention went to Rohit Arora, a PhD student at McCombs School of Business (University of Texas, Austin).
A Reinforcement-Learning Approach to Credit Collections
(M. Mark, N. Chehrazi, T.A. Weber)
This paper develops a dynamic reinforcement-learning agent capable of finding high-quality policies for the practice of debt collections. At its core, the agent effectively learns how to control a stochastic self-exciting point process in order to maximize an asynchronously obtained reward. Because we use the general formulation of the problem as an agent-environment interaction our results are readily extensible beyond the presented application. Furthermore, with the growing need for interpretable machine-learning models we provide a policy regularization technique which makes learned policies intuitively understandable for human decision makers. Finally, our implementation features a novel “guided exploration" mechanism which improves the agent's performance in hard-to-reach states.