Towards a Better Microcredit Decision

TL;DR

This paper introduces a multi-stage interaction sequence model for microcredit decision-making, capturing sequential dependencies and causal relationships to improve repayment prediction and address population bias.

Contribution

It proposes a novel multi-stage architecture with hierarchical attention and semi-supervised learning to better model sequential loan process interactions.

Findings

Improves repayment prediction accuracy.

Remedies population bias in credit modeling.

Enhances model generalization on real data.

Abstract

Reject inference comprises techniques to infer the possible repayment behavior of rejected cases. In this paper, we model credit in a brand new view by capturing the sequential pattern of interactions among multiple stages of loan business to make better use of the underlying causal relationship. Specifically, we first define 3 stages with sequential dependence throughout the loan process including credit granting(AR), withdrawal application(WS) and repayment commitment(GB) and integrate them into a multi-task architecture. Inside stages, an intra-stage multi-task classification is built to meet different business goals. Then we design an Information Corridor to express sequential dependence, leveraging the interaction information between customer and platform from former stages via a hierarchical attention module controlling the content and size of the information channel. In addition, semi-supervised loss is introduced to deal with the unobserved instances. The proposed multi-stage interaction sequence(MSIS) method is simple yet effective and experimental results on a real data set from a top loan platform in China show the ability to remedy the population bias and improve model generalization ability.