A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis
Highlights
► This paper presents a multi-industry investigation of the bankruptcy. ► The bankruptcy of Korean companies is predicted using neural network. ► The study intends to suggest the industry specific model to predict bankruptcy.
Introduction
Prediction of corporate bankruptcy is of a great concern to investors/creditors, borrowing firms, and governments. As a result of the collapse of Enron, many voices have called for a revolution of existing bankruptcy warning systems to detect or prevent bankruptcy problems in real time. Bankruptcy can happen to any organizations because the business environment is increasingly undergoing uncertainty and competition these days. The reduction of creditors’ risk and a considerable amount of saving for an economy can be possible from even a slight improvement with respect to assessing credit risk. An improvement in accuracy of even a fraction of a percent in scoring models to estimate the probability of default leads to enormous future savings for the credit industry (West, Dellana, & Qian, 2005). Assessment of bankruptcy offers invaluable information by which governments, investors, shareholders and the management can make their financial decisions in order to prevent possible losses. The study of bankruptcy provides an early warning signal and detects areas of weaknesses. Accurate bankruptcy prediction usually leads to many benefits such as cost reduction in credit analysis, better monitoring, and an increased debt collection rate.
A number of publications have pursued this subject and extending conventional models for prediction during the past 50 years. The number of bankruptcy prediction models has grown enormously due to the growing availability of data and the development of improved econometrical techniques during the 1980s and 1990s. Most of this work has been influentially led by a small number of early papers (e.g., Altman, 1968, Ohlson, 1980, Zavgren, 1985) on US quoted companies. The methods for bankruptcy prediction can be grouped in two categories: statistical and artificial intelligence models. The first group consists of Logit, multivariate discriminant analysis, etc. The tool first applied to bankruptcy prediction was the univariate data analysis proposed by Beaver (1966), which was followed by the multi-variate discriminant analysis and regressions (Ohlson, 1980). The second group includes neural networks (Chauhan et al., 2009, Cho et al., 2009, Pendharkar, 2005, Tseng and Hu, 2010), genetic algorithms (Etemadi et al., 2009, Lensberg et al., 2006), and support vector machine (Min and Lee, 2005, Yang et al., 2011), and case based reasoning (Cho Hong & Ha, 2010). While some of these models show high predictive accuracy levels, the absence of bankruptcy theory makes attempts to establish a generally accepted model for bankruptcy prediction unsuccessful.
Although the discriminant analysis and linear regression model have become the most commonly used in bankruptcy prediction, their inherent drawbacks of statistical assumptions such as linearity, normality and independence among variables have constrained both applications. Recent trends in the development of artificial intelligence have brought forth new alternatives in solving nonlinear problems. The expert system, fuzzy logic, and neural networks are a great help to a manager in predicting bankruptcy making decisions. Neural networks have many different topologies for problem dissimilarities. Among them, back-propagation is the most well known and commonly used, categorized as one of the supervised learning models. It draws the mapping function between the input and output from the provided data set. The back propagation neural network (BPN) usually contains one input layer, one or two hidden layer(s) and one output layer. Each layer of a neural network structure has several units and output units of a layer are input units of its next layer. The purpose of back-propagation training is to produce the weight of each edge, in order to minimize the squared error sum between the actual value and the predicted value.
Previous studies on neural network applications for bankruptcy prediction have been targeting single industry or not investigated the industry difference in bankruptcy prediction. For example, He and Kamath (2005) evaluated the effectiveness of two successful bankruptcy models by Ohlson (1980) and Shumway (2001) with the help of a mixed industry sample in discriminating between bankrupt and non bankrupt firms from an individual industry the equipment & machinery manufacturing (EMM) industry. Dewaelheyns and Van Hulle (2006) suggested that models involving both bankruptcy variables defined at subsidiary level and at group level provide a substantially better fit and classification performance. These studies did not examine the difference in industries in terms of independent variables, prediction accuracy, and practically usable models. It is still elusive whether generic prediction models are still successful in predicting individual industry. Further, although there exist a number of studies on using neural networks on bankruptcy prediction, the studies on using multi-industry data and developing models for multi-industry are almost rare. This paper intends to fill this void. This paper focuses on the different back propagation neural network (BNN) models for construction, retail, and manufacturing industries. This study intends to show the optimal tested for each industry by using the bankruptcy data of Korean companies. The study includes the comparison of predictive accuracy with multivariate discriminant analysis (MDA) and shows the implications of difference in prediction models and results.
Section snippets
Theoretical background
The credit risk analysis was pioneered by Beaver (1966). The author suggested cutoff threshold values for financial ratio variables in terms of profitability, liquidity, and solvency in order to classify them into two groups. The earliest studies about bankruptcy prediction were adopting the statistical approaches upon empirical data. Altman (1968) developed a statistical linear model and computed an individual firm’s discriminant score to estimate the likelihood of bankruptcy. Altman used a
Variables selection
In bankruptcy prediction, the main concern of interest is to construct the prediction model representing the relationship between the bankruptcy and financial ratios and then deploy the model to identify the high risk of failure in the future. A large number of features are usually included so that the training data is not enough to cover the decision space, which is represented as the curse of dimensionality. Feature selection represents the problem by excluding unimportant, redundant and
Methods
In order to extract the variables that are importantly related to bankruptcy in each industry, t-test and correlation analysis are used in establishing the industry prediction model for BNN and MDA. The hit ratio is compared between BNN and MDA using t-test. KIS database is used for extracting the sample of the study.
The companies that became officially bankrupt from January 1, 2000 to December 31 2009 which became delisted from Korea Stock Exchange, comprised the bankrupt companies in the
Selection of input variables
Using t-test, the significant variables which differ across bankrupt group and non-bankrupt group were selected from 100 financial ratios available in each record. The t-test to extract the important variables for being related to bankruptcy results in 46, 40, and 58 significant variables for construction, retail, and manufacturing industry at 0.05 significance level. For these selected variables, the correlation analysis was performed to select the variables which is most related to
Conclusions and implications
This study provides the multi-industry bankruptcy prediction model while previous studies are largely lacking in offering industry-specific model for bankruptcy prediction. This study intends to select the different group of independent variables to predict bankruptcy for construction, retail, and manufacturing industry. The study presented multi-industry prediction model using accounting-based measures as variables to predict bankruptcy and showed that financial ratios provide early warning
References (28)
- et al.
Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural networks (the Italian experience)
Journal of Banking & Finance
(1994) - et al.
Differential evolution trained wavelet neural networks: Application to bankruptcy prediction in banks
Expert Systems with Applications
(2009) - et al.
Alternative diagnosis of corporate bankruptcy: A neuro fuzzy approach
Expert Systems with Applications
(2009) - et al.
A hybrid approach based on the combination of variable selection using decision trees and case-based reasoning using the Mahalanobis distance; for bankruptcy prediction
Expert Systems with Applications
(2010) - et al.
An integrative model with subject weight based on neural network learning for bankruptcy prediction
Expert Systems with Applications
(2009) - et al.
A genetic programming model for bankruptcy prediction: Empirical evidence from Iran
Expert Systems with Applications
(2009) - et al.
Bankruptcy theory development and classification via genetic programming
European Journal of Operational Research
(2006) - et al.
Bankruptcy prediction using support vector machine (SVM) with optimal choice of kernel function parameters
Expert Systems with Applications
(2005) A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem
Computers & Operations Research
(2005)- et al.
Comparing four bankruptcy prediction models: Logit, quadratic interval logit, neural and fuzzy neural networks
Expert Systems with Applications
(2010)
Neural network ensemble strategies for financial decision applications
Computers & Operations Research
Using partial least squares and support vector machines for bankruptcy prediction
Expert Systems with Applications
Integrating artificial neural networks with rule-based expert systems
Decision Support Systems
Earnings quality, bankruptcy risk and future cash flows
Accounting and Business Research
Cited by (122)
Combining intra-risk and contagion risk for enterprise bankruptcy prediction using graph neural networks
2024, Information SciencesAutomated Machine Learning in Bankruptcy Prediction of Manufacturing Companies
2024, Procedia Computer ScienceThe evaluation of bankruptcy prediction models based on socio-economic costs
2023, Expert Systems with ApplicationsBankruptcy prediction using fuzzy convolutional neural networks
2023, Research in International Business and FinanceNo more black boxes! Explaining the predictions of a machine learning XGBoost classifier algorithm in business failure
2022, Research in International Business and FinanceDeep reinforcement learning with the confusion-matrix-based dynamic reward function for customer credit scoring
2022, Expert Systems with Applications