SME Default Prediction Framework with the Effective Use of External Public Credit Data

Zhichao Luo,Pingyu Hsu,Ni Xu

doi:10.3390/su12187575

Zhichao Luo, Pingyu Hsu + Show 1 more

Open Access

https://doi.org/10.3390/su12187575

Copy DOI

Journal: Sustainability	Publication Date: Sep 14, 2020
Citations: 9	License type: CC BY 4.0

Affiliation: National Central University

Abstract

Traditional default prediction models mainly rely on financial data. However, financial data on small and medium-sized enterprises (SMEs) are difficult to obtain, and even when they are available, their opaqueness may hinder analysis. Therefore, traditional prediction models encounter serious problems when being utilized to predict the defaulting of SMEs. In this paper, a novel prediction framework utilizing only external public credit data is proposed. The external public credit data used include SMEs’ basic information (BI), credit information from the government (CIG), and court verdict information (CVI), which can be collected from publicly accessible websites. Records on 15,605 sample companies were collected from approximately 300,000 companies. Among them, 8183 have defaulted. The empirical data were applied to construct prediction models using logistic regression, the classification and regression tree (CART) model, and LightGBM. The best results achieved 0.87 accuracy and 0.92 area under receiver operating characteristic (AUC). The results show that the model only uses the external credit data proven to have significant predict ability, and CIG variables offer the best prediction capacities.

Highlights

Small and medium-sized enterprises (SMEs) constitute the backbone of national economies in many countries
The hold out method was employed to verify the validity of the proposed model where 80% of the collected data were reserved for training while the remaining 20% were used for testing and logistic regression
It reveals that registered capital (RC), Age, TCC_B, TTC_D, TCC_M, tax regulation infringements (TTRI), TRGI, and the number of lawsuits (TS) significantly influence the default variable

Summary

Introduction

Small and medium-sized enterprises (SMEs) constitute the backbone of national economies in many countries. SMEs are the predominant types of businesses involved in Organization for Economic Cooperation and Development economics and typically account for two-thirds of all employment [1]. They make strong positive contributions to bank profitability [2]. SMEs contribute considerably to economic and bank profitability; on the other hand, lending to SMEs may come with greater risks than lending to large corporations. This dilemma has attracted considerable research interest among both academics and practitioners. Since the groundbreaking work of [5], many default prediction models focusing on SMEs and utilizing various cooperate financial indicators have been proposed [6,7,8,9]

Methods

Results

Conclusion