Neural Networks in Credit Risk Classification of Companies in the Construction Sector

Aleksandra Wójcicka

doi:10.33119/erfin.2017.2.2.1

Abstract

The financial sector (banks, financial institutions, etc.) is the sector most exposed to financial and credit risk, as one of the basic objectives of banks' activity (as a specific enterprise) is granting credit and loans. Because credit risk is one of the problems constantly faced by banks, identification of potential good and bad customers is an extremely important task. This paper investigates the use of different structures of neural networks to support the preliminary credit risk decision-making process. The results are compared among the models and juxtaposed with real-world data. Moreover, different sets and subsets of entry data are analyzed to find the best input variables (financial ratios).

Highlights

The history of bank systems indicates that the main reasons for decreasing potential profits or capital and the occurrence of financial difficulties are an inefficient credit granting policy, faulty credit procedures of credit norms and regulations, and insufficient collateral for loans
This paper investigates the use of different structures of neural networks to support the preliminary credit risk decision-making process
In the process of ratio selection, the rejected ratios were as follows: quick ratio, stock turnover ratio, gross profit margin ratio, equity debt ratio, short-term investments turnover ratio, equity profitability ratio, sale profitability ratio, self-financing ratio, operating ratio, sales dynamics, receivables to liabilities ratio, costs increase ratio, long-term debt ratio, debt/EBITDA, EBITDA/financial expenses, current assets turnover ratio, and operating activity profitability ratio. It appears that the best set of ratios for multilayer perceptron (MLP) consists of eight following ratios: current ratio, receivables ratio, net profit margin ratio, financial surplus rate, total debt ratio, costs level ratio, assets profitability ratio, and financial leverage

Summary

Introduction

The history of bank systems indicates that the main reasons for decreasing potential profits or capital and the occurrence of financial difficulties are an inefficient credit granting policy, faulty credit procedures of credit norms and regulations, and insufficient collateral for loans. It affects various economic branches, and decisions made within them, to a different extent. Credit risk is broadly conceived as the probability of non-repayment of bank financial resources granted to debtors (enterprises). The most important element for categorizing debtors as ‘good’ or ‘bad’ is a prior identification of factors that affect the condition of companies.

Objectives

Methods

Results

Conclusion