Reinforcement Learning in Credit Scoring and Underwriting

TL;DR

This paper introduces a reinforcement learning framework for credit scoring and underwriting, proposing new algorithms that improve decision-making and outperform traditional methods in certain scenarios.

Contribution

It adapts RL principles to credit underwriting, incorporating action space renewal and multi-choice actions, and introduces two novel RL-based algorithms for better credit decision-making.

Findings

New RL algorithms outperform traditional methods in aligned data scenarios

Traditional underwriting aligns with RL greedy strategy

Model limitations are evident in complex situations

Abstract

This paper proposes a novel reinforcement learning (RL) framework for credit underwriting that tackles ungeneralizable contextual challenges. We adapt RL principles for credit scoring, incorporating action space renewal and multi-choice actions. Our work demonstrates that the traditional underwriting approach aligns with the RL greedy strategy. We introduce two new RL-based credit underwriting algorithms to enable more informed decision-making. Simulations show these new approaches outperform the traditional method in scenarios where the data aligns with the model. However, complex situations highlight model limitations, emphasizing the importance of powerful machine learning models for optimal performance. Future research directions include exploring more sophisticated models alongside efficient exploration mechanisms.