Banka başarısızlıklarının yapay sinir ağlarıyla tahmini: Türk bankacılık sistemi üzerine karşılaştırmalı bir uygulama

Translated title of the contribution: Bank Failure Prediction with Artificial Neural Networks: A Comparative Application to Turkish Banking System

Murat Mazibas, Unsal Ban

    Research output: Contribution to journalArticlepeer-review

    Abstract

    In this study, neural network models are introduced and employed for the classification of failed non-failed banks prior to the failure of banks. To perform classification 36 financial and operational ratio of banks operating in Turkey were used as an input to the models. Two types of neural network structure were employed: Multilayer Perceptron (MLP) and Generalized Feed Forward Networks (GFW). Based on these network structures ten Artificial Neural Network (ANN) model were constructed having a varying number of hidden layers and perceptron in each layer. Rival models are evaluated and compared in terms of classification accuracy. Models are estimated for 1995-2000 period prior to bank failures. In addition to ANN models, to compare the classification performance, discriminant and logistic regression models are employed. Comparison of classification performance of ANN, discriminant and logistic regression models yield that ANN outperforms other models.
    Translated title of the contributionBank Failure Prediction with Artificial Neural Networks: A Comparative Application to Turkish Banking System
    Original languageMultiple languages
    Article number2
    Pages (from-to)27-53
    Number of pages27
    JournalIktisat Isletme ve Finans
    Volume24
    Issue number282
    Publication statusPublished - Sep 2009

    Keywords

    • bank failure prediction
    • failed bank classification
    • neural networks
    • Multilayer Perceptron Networks
    • Generalized Feed Forward Network
    • discriminant analysis
    • logistic regression analysis
    • Turkish banking system

    Fingerprint

    Dive into the research topics of 'Bank Failure Prediction with Artificial Neural Networks: A Comparative Application to Turkish Banking System'. Together they form a unique fingerprint.

    Cite this