Bankruptcy prediction for SMEs using transactional data and two-stage multiobjective feature selection

TLDR

Bankruptcy prediction for SMEs has largely depended on accounting ratios, yet adding many such features creates high‑dimensional problems that reduce interpretability and raise acquisition costs. This study aims to develop a bankruptcy prediction model for SMEs that relies solely on transactional and payment‑network data, eliminating the need for accounting information. The authors employ a two‑stage multi‑objective feature‑selection procedure that simultaneously minimizes feature count and maximizes classification performance using these transactional variables. Offline and online experiments demonstrate that the resulting model matches the predictive accuracy of traditional approaches while drastically reducing the feature set, and feature‑importance analysis confirms the critical role of transactional and payment‑network variables.

Abstract

Many bankruptcy prediction models for small and medium-sized enterprises (SMEs) are built using accounting-based financial ratios. This study proposes a bankruptcy prediction model for SMEs that uses transactional data and payment network–based variables under a scenario where no financial (accounting) data are required. Offline and online test results both confirmed the predictive capability and economic benefit of transactional data–based variables. However, incorporating those features in predictive models produces high dimensional problems, which deteriorates model interpretability and increases feature acquisition costs. Thus, we propose a two-stage multiobjective feature-selection method that optimizes the number of features as well as model classification performance. The results showed that the proposed model achieved similar classification performance while greatly reducing the cardinality of the feature subset. Finally, the feature importance evaluation for features in the optimal subset confirmed the importance of transactional data and payment network-based variables for bankruptcy prediction.