A comparison of supervised and unsupervised neural networks in predicting bankruptcy of Korean firms

Lee, Ki-Dong; Booth, David E.; Alam, Pervaiz

doi:10.1016/j.eswa.2005.01.004

Cited by 183 publications

(72 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We note that this type of error is always very low in any of years studied, indeed it never exceeds 3.1%. These results are superior to those obtained in similar comparative analysis studies (Frydman et al, 1985;Koh Tan, 1999;Lennox, 1999;Min & Lee, 2005;Lee et al, 2005).…”

Section: Rough Setscontrasting

confidence: 55%

Comparative Analysis between Statistical and Artificial Intelligence Models in Business Failure Prediction

Pereira¹,

Basto²,

Silva³

2014

JMS

View full text Add to dashboard Cite

A growing number of predicting corporate failure models has emerged since 60s. Economic and social consequences of business failure can be dramatic, thus it is not surprise that the issue has been of growing interest in academic research as well as in business context.The main purpose of this study is to compare the predictive ability of five developed models based on three statistical techniques (Discriminant Analysis, Logit and Probit) and two models based on Artificial Intelligence (Neural Networks and Rough Sets). The five models were employed to a dataset of 420 non-bankrupt firms and 125 bankrupt firms belonging to the textile and clothing industry, over the period 2003-09. Results show that all the models performed well, with an overall correct classification level higher than 90%, and a type II error always less than 2%. The type I error increases as we move away from the year prior to failure.Our models contribute to the discussion of corporate financial distress causes. Moreover it can be used to assist decisions of creditors, investors and auditors. Additionally, this research can be of great contribution to devisers of national economic policies that aim to reduce industrial unemployment.

show abstract

Section: Rough Setscontrasting

confidence: 55%

Comparative Analysis between Statistical and Artificial Intelligence Models in Business Failure Prediction

Pereira¹,

Basto²,

Silva³

2014

JMS

View full text Add to dashboard Cite

show abstract

“…The sample population include 133 pairs of bankrupt and healthy firms accepted in South Korean stock exchange. Lee et al (2005) found that BP algorithm worked better than that of Kohonen. Doumpos et al (2005) adopted support vector machine in a sample including 1754 British firms in the period of 1998 to 2003 to create linear and nonlinear models for the prediction of the type of auditor's opinion.…”

Section: Literature Reviewmentioning

confidence: 99%

The Investigation and Comparison of the Performance of Heuristic Methods in the Prediction of the Type of Auditor’s Opinion in Firms Accepted in Tehran Stock Exchange

Nasirpour¹,

Mazdaki²,

Enayati³

2016

ASS

View full text Add to dashboard Cite

Stock companies play a key role in the economy of any country and the success of these companies depends to a great degree on investors and creditors' interest who invest in them. Auditors' reports assume a special position in the decisions taken by investors and creditors. Therefore, the importance of offering high quality information with a view on recent events in the firms (bankruptcy and dissolution, financial scandals, loses suffered by creditors, etc.) becomes clear; moreover, audit reports can prevent these events by creating certain signals. To this end, modern heuristic methods for the prediction of the type of auditor's opinion are offered in this paper. The aim of this study is to investigate the ability of probabilistic neural network method and to compare it with artificial neural network in order to identify and predict the type of independent auditor's opinion in Iran in the time period of 2009 to 2013. The patterns used to predict the type of independent auditor's opinion can be divided into different categories-these categories are becoming more complex and more advanced: single-variable models, multi discriminant analysis, regression function, neural networks, etc. neural networks are getting increasing popularity among researchers for their non-linear and non-parametric properties. Therefore, modern approaches are used in this study to predict the type of auditor's opinion.

show abstract

“…Historical overview of model's creation is stated in table 1. The newest models are for example Ahn and Kim's hybrid case-based reasoning and genetic algorithm (Ahn & Kim, 2009), the model based on the neural networks (Lee, Booth & Alam, 2005), combination of random subspace approach and binary logit model (Li, Lee, Zhou & Sun, 2011), hazard model based model (Shumway, 2001). The newest Czech models are bankruptcy index with accuracy 80.28% (Karas & Režnáková, 2014) and the model created using the sample of plastic producers and metal manufacturing companies with accuracy 90.96% (Homolka, Doležal & Novák, 2014).…”

Section: Introductionmentioning

confidence: 99%

Interconnection between Achieved Level of Return on Equity and Evaluation Scale of the Kralicek´S Model

Kuběnka

2014

ijmsba

View full text Add to dashboard Cite

A large number of diagnostic and predictive models exists using different or no statistical methodology. Often, diagnostic and predictive models differ in focus on branch of company, size of company, tradability of shares, country of usage, and focus on maturity of the market environment. Many of the models are widely used, however, their explanatory power is not known. Good examples of these models are those used in banks in the process of credit worthiness assessment. Some of them are created based on the Q-Test model. However, not only banks need to check the financial situation of companies but also basic users like suppliers, customers and other business partners. This article deals with Kralicek´s Q-Test which is one of the well-known financial diagnostic models in Europe including the Czech Republic. Its five grade rating scale reveals little about the level of prosperity of analysed companies. An assumption exists that grade 1 means excellent financial health. However what exactly does it mean? Can it be assumed that this means a negligible to zero probability of bankruptcy and simultaneously a sufficient or a high profitability?The question is what is the level of prosperity connected with the grades achieved on the Q-Test evaluation scale from1to 5. The prosperity of the company is uniquely linked to the return on equity. Another question is whether the QTest is able to express a level of prosperity and not only a level of creditworthiness of companies. That is why the research based on analysis of dataset of 1504 Czech companies was carried out. Following the research a scale was made of achieved return on equity (ROE). ROE levels are expressed by the following: implicit cost of equity (r e ), riskfree rate (r f ), positive ROE, negative ROE and negative equity (or insolvency). The researched found that the Q-Test's informative value is comparable to the predictive models based on statistic techniques.

show abstract

A comparison of supervised and unsupervised neural networks in predicting bankruptcy of Korean firms

Cited by 183 publications

References 35 publications

Comparative Analysis between Statistical and Artificial Intelligence Models in Business Failure Prediction

Comparative Analysis between Statistical and Artificial Intelligence Models in Business Failure Prediction

The Investigation and Comparison of the Performance of Heuristic Methods in the Prediction of the Type of Auditor’s Opinion in Firms Accepted in Tehran Stock Exchange

Interconnection between Achieved Level of Return on Equity and Evaluation Scale of the Kralicek´S Model

Contact Info

Product

Resources

About