THE COMPARISION OF THE FINANCIAL FAILURE WITH ARTIFICIAL NEURAL NETWORK AND LOGIT MODELS

Abstract

The purpose of this study is to predict of the financial failure of the companies traded at the Istanbul Stock Exchange, determine the financial rates affecting the financial failure and build a model by which companies having a financial failure risk could be detected. For this purpose, experiment set data and financial failure model have been estimated by using artificial neural network and logit models. The performances of artificial neural network and logit models have been compared by the analysis of the control set data and validity of these models. The 2008-2013 data of the manufacturing industry companies traded at Istanbul Stock Exchange have been used and, distinctly from the similar studies in the literature, along with the model in which all failure criteria exist, three different models, where the criteria of making loss in two or more consecutive years and debt surpassing active are handled, have been built and the effects of the criteria on financial failure have been compared.    At the end of the study, in the determination of the financial failure, the fact that debt surpassing active is much more effective than making loss in 2 or more consecutive years has been supported with both artificial neural network and logit model results. In financial failure studies, some findings about the fact that debt surpassing active is a more important indicator have been obtained. Furthermore, the fact that the most important rates affecting financial failure are liquidity and financial structure rates has been determined with the models built.

Keywords

• Financial failure

References

1. • Abdullah, N.A. (2008), “Predicting Corporate Failure of Malaysia’s Listed Companies: Comparing Multiple Discriminant Analysis Logistic Regression and Hazard Model”, International Research Journal of Finance and Economics, Issue: 15, 201-218
2. • Aktaş, Ramazan. Doğanay, Mete and Yıldız, Birol (2003), “Mali Başarısızlığın Öngörülmesi: İstatistiksel Yöntemler ve Yapay Sinir Ağı Karşılaştırması”, Ankara Üniversitesi SBF Dergisi, 58-4
3. • Akkaya, Göktuğ Cenk. Demireli, Erhan and Yakut, Ümit Hüseyin(2009), “İşletmelerde Finansal Başarısızlık Tahminlemesi Yapay Sinir Ağları Modeli ile İMKB Üzerine Bir Uygulama”, Eskişehir Osmangazi Üniversitesi Sosyal Bilimler Dergisi, 10(2) 187
4. • Aldrich, John Herbert. ve Nelson, Forrest (1984), “Linear Probability, Logit, And Probit Models”, Sage University Papers Series. Quantitative Applications İn The Social Sciences ,
5. • Allison, P (2012), “Logistic Regression Regression Models: Theory And Implementation Using”, Sas®: Theory And Application, Second Edition
6. • Altman, Edward I. (1968), “Financial Ratios, Discriminant Analysis And Prediction Of Corporate Bankruptcy”, The Journal Of Finance, 23 (4): 589-590.
7. • Altman,E. Marco G and Varetto,F. (1994), “Corporate Distress Diagnosis: Comparisons Using Linear Discriminant Analysis And Neural Networks”, Journal Of Banking & Finance, 18,Pp. 505–529
8. • Chung,Kim-Choy. Tan, Shin and Holdsworth, David K. (2008), “Insolvency Prediction Model Using Multivariate Discriminant Analysis And Artificial Neural Network For The Finance Industry İn New Zealand”, International Journal Of Business And Management, 3 (1): 19-29.