Predicting Financial Failure of the Turkish Banks

Abstract

Banks are the most important financial institutions in Turkey because other financial institutions are not developed efficiently yet. Turkish banks experienced financial difficulties and a substantial amount of banks failed in the past. This event urged the government to initiate measures to prevent banks from getting into financial difficulties. As a result of these measures, Turkish banking system currently seems to be very attractive for the foreign investors willing to invest in this sector. One of the main concerns of the foreign investors is a possibility of a new banking crisis although it is very remote at this time. The purpose of this study is to develop early warning systems predicting the financial failure at least three years ahead of financial failure date. A number of multivariate statistical models such as multiple regression, discriminant analysis, logit, probit are used. We found that the most appropriate model is logit. The significant variables obtained from the models explain very well the causes of the bank failures. Our models can be used to assist interested parties to predict the probability of financial failure of Turkish banks.

Financial Leading Indicators of Banking Distress: A Micro Prudential Approach - Evidence from Europe

“…This improves another time that the neural network method outperforms the two others (logit and discriminant analysis). These results confirm those obtained by Giovanis, (2010) and would be contrary to the result reached by Doganay, (2006) according to which logit is the best model to predict bank distress.…”

“…Among these methods we can notice: Discriminant analysis (Sinkey, 1975;Altman, 1968;Lin, 2009;Giovanis, 2010;Kouki & Elkhaldi, 2011), logistic regression (Thomson, 1991;Gonzalez-Hermosillo, 1999;Godlewski, 2004;Montgomery, Hanh, Santoso, & Besar, 2005;Lin, 2009;Giovanis, 2010;Messai & Jouini, 2013a). We could also notice that the Probit regression is a multivariate statistical method that was used to predict bankruptcies for some ailing banks (Barr & Siems, 1994;Doganay, Ceylan, & Aktas, 2006;Lin, 2009;Wong et al, 2010 Similarly, Konstandina (2006) used logit analysis to predict the failure of Russian banks. She used 6 macroeconomic factors and 13 factors specific to banks as independent variables.…”

Delisting Risk Analysis: Empirical Evidence from the Thai Listed Companies

“…A variety of statistical methods and neural networks approach have been applied for predicting problems. Statistical methods; e.g., linear discriminant analysis (LDA) , multivariate discriminant analysis (MDA) (Altman, 1968;Sinkey, 1975;Altman, 1977;Lam and Moy, 2002), factor analysis (FA), probit, and logistic regression (logit) (Zmijewski,1984;Martin, 1977;Ohlson, 1980;Thomson, 1991;Gonzalez-Hermosillo, 1999;Kolari, et al, 2002;Montgomery et al, 2005;Canbas, 2005;Konstandina, 2006;Doganay et al, 2006) are widely used. This study employs logistic regression to predict the probability of delisting of a firm from Securities and Exchange Commission (SEC) and attempts to assess the prediction power of logistic regression.…”

Constructing financial distress prediction model using group method of data handling technique

“…Doganay et al [9] constructed an early warning model by integrating multiple regression, discriminant analysis, probit and logit.…”

“…Therefore, financial distress prediction becomes more and more important because it is helpful for managers and relevant authorities who can prevent the occurrence of failures and for decision-makers of financial institutions or investors to evaluate and select firms to invest in [7,30]. Early studies used statistical methods such as multiple descriminant analysis [1,2,3,8,11,14,27,28], logistic regression [6,9,13,17,22], and multiple regression to predict business failures. Since the rapid development of artificial intelligence, artificial neural networks (ANN) were also utilized to financial distress prediction [4,5,10,15,16,19,20,21,23,24,25,26,30,31].…”