Mevduat Bankalarının Karlılığının Yapay Sinir Ağları ile Tahmini: Bir Yazılım Modeli Tasarımı

Yıl 2015, Cilt: 9 Sayı: 1, 9 - 46, 01.06.2015

Ferdi Sönmez Metin Zontul Şahamet Bülbül

Öz

Son yıllarda karlılık analizlerinde; esnek hesaplama EH teknikleri, doğrusal olmayan çok değişkenli veri yapısında başarılı uygulamalarından dolayı tercih edilmektedir. Ancak, EH kullanımında karşılaşılan birtakım yetersizlikler nedeniyle, adaptif bir sisteme gereksinim duyulmuştur. Makalenin amacı; aktif karlılığı ve özkaynak karlılığı ile ifade edilen banka karlılığı üzerinde etkisi olan değişkenlerin kullanılmasıyla ve ilk defa geliştirilecek adaptif bir yazılım modeli ile Türkiye'deki mevduat bankalarının karlılığını önemli bir EH tekniği olan yapay sinir ağları ile analiz etmektir. Modelden çıkan sonuçlar, kullanılan değişkenlerin tamamının karlılık üzerinde değişen oranlarda önemli etkisinin olduğunu ve tahminlerin hedeflenen ve kabul edilebilir başarı performansını yakaladığını göstermektedir. Bu başarılı sonuçlarından dolayı ve kullanıcı farklılıklarından etkilenmemesine de bağlı olarak, bu yazılım modelinin; banka karlılığı tahmininde kolaylıklar sağlayacağı düşünülmektedir

Anahtar Kelimeler

Banka Karlılığı, Türk Bankacılık Sektörü, Esnek Hesaplama Teknikleri, Yapay Sinir Ağları, Çok Katmanlı Algılayıcı, Levenberg–Marquardt Geri Yayılım Algoritması.

Estimating Deposit Banks Profitability with Artificial Neural Networks: A Software Model Design

Öz

Estimating Deposit Banks Profitability with Artificial Neural Networks: A Software Model Design In recent years, soft computing SC techniques have been preferred to measure bank profitability because of their successful applications in nonlinear multivariate situations. However, an adaptive system was needed due to the insufficient use of application software programs for SC. This paper is intended to measure profitability of deposit banks in Turkey with an adaptive SC software model of artificial neural networks which is developed for the first time and using variables that have impact on profitability. The results from the model indicate that all of the variables used have significant impact, in varying proportions, on profitability and that obtained estimations achieved the targeted and acceptable performance of success. This software model is expected to provide easiness on estimating bank profitability, since giving such successful estimations and not being affected by user differences

Anahtar Kelimeler

Bank Profitability, Turkish Banking Sector, Soft Computing Techniques, Artificial Neural Networks, Multilayer Perceptron, Levenberg Marquardt Back Propagation Algorithm.

Kaynakça

• Abreu, M. ve Mendes, V..(2001). Commercial Bank Interest Margins and Profi- tability: Evidence for Some EU Countries. Pan-European Conference Jointly Or- ganized by the IEFS-UK & University of Macedonia Economic & Social Sciences, Thessaloniki, Greece, 17-20.
• Afanasieff, T.S., Lhacer, P.M.V. ve Nakane, M.I..(2002). The Determinants of Bank Interest Spreads in Brazil. Banco Central di Brazil Working Papers, No:46.
• Albertazzi, U. ve Gambacorta, L..(2009). Bank Profitability and the Business Cy- cle. Journal of Financial Stability, 5 (4): 393-400.
• Alper, D. ve Anbar, A..(2011). Bank Specific and Macroeconomic Determinants of Commercial Bank Profitability: Empirical Evidence from Turkey. Business and Economics Research Journal, 2(2): 139-152.
• Altunöz, U..(2013). Bankaların Finansal Başarısızlıklarının Yapay Sinir Ağları Modeli Çerçevesinde Tahmin Edilebilirliği. Dokuz Eylül Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 28(2):189-217.
• Anastasakis,L. ve Mort, N..(2000) Neural Network-based Prediction of the USD/ GBP Exchange Rate: the Utilisation of Data Compression Techniques for Input Dimension Reduction. University of Sheffield, Technical Report.
• Anyaeche, C.O. ve Ighravwe, D.E..(2013). Predicting Performance Measures Using Linear Regression and Neural Network: A Comparison. African Journal of Engineering Research, 1(3): 84-89.
• Atasoy, H..(2007). Türk Bankacılık Sektöründe Gelir-Gider Analizi Karlılık Per- formansının Belirleyicileri, Uzmanlık Yeterlilik Tezi. Ankara: TCMB Bankacılık ve Finansal Kuruluşlar Genel Müdürlüğü.
• Athanasoglou, P., Delis, M.D. ve Staikouras, C..(2006). Determinants of Bank Profitability in the South Eastern European Region, Bank of Greece Working Papers, No:47.
• Athanasoglou, P.P., Brissimis, S.N. ve Delis, M.D..(2008). Bank-specific, Industry- specific and Macroeconomic Determinants of Bank Profitability. Journal of Inter- national Financial Markets, Institutions and Money, 18: 121–136.
• Aysan, A.G. ve Abbasoğlu, O.F..(2007). Concentration, Competition, Efficiency and Profitability of the Turkish Banking Sector in the Post-Crises Period. Banks and Bank Systems, 3(2): 106-115.
• Bankacılık Düzenleme ve Denetleme Kurumu, (2013) Türk Bankacılık Sektörü Genel Görünümü Aralık 2013, www.bddk.org.tr.
• Bashir, A-H.M..(2000). Determinants of Profitability and Rate of Return Margins in Islamic Banks: Some Evidence from the Middle East. 8th ERF Conference, Jordan.
• Bessis, J..(2010). Risk Management in Banking, 3rd Edition, İngiltere: John Wiley & Sons.
• Boyacıoğlu, M.A., Kara, Y. ve Baykan, Ö.K..(2009). Predicting Bank Financial Failures Using Neural Networks, Support Vector Machines and Multivariate Sta- tistical Methods:A Comparative Analysis in the Sample of Savings Deposit Insur- ance Fund (SDIF) Transferred Banks in Turkey. Expert Systems With Applica- tions, 36: 3355–3366.
• Cao, L..(2003). Support Vector Machines Experts for Time Series Forecasting. Neurocomputing, 51: 321-329.
• Chang, T., Yang, S. ve Chang, K..(2009). Portfolio Optimization Problems in Different Risk Measures Using Genetic Algorithm. Expert Systems with Applica- tions, 36(7): 10529-10537.
• Chen, M-Y., Fan, M-H., Chen, Y-L. ve Wei, H-M..(2013). Design of Experiments on Neural Network’s Parameters Optimization for Time Series Forecasting in Stock Markets. Neural Network World, 4(13): 369-393.
• Curak, M., Poposki, K. ve Pepur, S..(2012). Profitability Determinants of the Macedonian Banking Sector in Changing Environment. Procedia - Social and Behavioral Sciences, 44: 406-416.
• Demuth, H., Beale, M. ve Hagan, M..(2009). Neural Network Toolbox 6 User’s Guide. Natick, MA: The MathWorks, Inc.
• Dietrich, A. ve Wanzenried, G..(2011). Determinants of Bank Profitability Before and During the Crisis: Evidence from Switzerland. Journal of International Finan- cial Markets, Institutions & Money, 21: 310-320.
• Duvan, O.B. ve Yurtoğlu, H..(2004). Determinants of Bank Provisions: Evidence from Turkey. Journal of Economic Cooperation, 25(4): 105-110.
• Fanning, K.M ve Cogger K.O..(1994). A Comparative Analysis of Artificial Neu- ral Networks Using Financial Distress Prediction. Intelligent Systems in Account- ing, Finance and Management, 3(4): 241-252.
• Girden E.R..(2001). Evaluating Research Articles from Start to Finish. Thousand Oaks, CA: Sage Publications.
• Güngör, B..(2007). Türkiye’de Faaliyet Gösteren Yerel ve Yabancı Bankaların Karlılık Seviyelerini Etkileyen Faktörler: Panel Veri Analizi. İktisat İşletme ve Fi- nans, 22(258): 40-63.
• Hagan, M.M. ve Menhaj, M.B..(1999). Training Feed-Forward Networks with the Marquardt Algorithm. IEEE Transactions on Neural Networks, 6(5): 989–991.
• Han, Y. ve Wang, B..(2011). Investigation of Listed Companies Credit Risk As- sessment Based on Different Learning Schemes of BP Neural Network. Interna- tional Journal of Business and Management, 6(2): 204-207.
• Hassan, M.K. ve Bashir, A-H.M..(2003). Determinants of Islamic Banking Profi- tability. Paper presented at the Economic Research Forum (ERF) 10th Annual Conference, Marrakech, Morocco.
• Haykin, S..(2009). Neural Networks and Learning Machine, 3E. NJ: Pearson Edu- cation Inc.
• Hippert, H.S., Pedreira, C.E. ve Souza, R.C..(2001). Neural Networks for Short- Term Load Forecasting: A Review and Evaluation. IEEE Transactıons on Power Systems, 16(1): 44-55.
• Jiang, G., Tang, J.N., Law, E. ve Sze, A..(2003). The Profitability of Banking Sec- tor in Hong Kong. Hong Kong Monetary Authority Quarterly Bulletin, No:36.
• Kalaycı S..(2010). SPSS Uygulamalı Çok Değişkenli İstatistik Teknikleri. Ankara: Asil Yayınları.
• Kanas, A., Vasiliou, D. ve Eriotis, N..(2012). Revisiting Bank Profitability: A Semi- Parametric Approach. Journal of International Financial Markets, Institutions and Money, 22(4): 990-1005.
• Kaya Türker, Y..(2002). Türk Bankacılık Sektöründe Karlılığın Belirleyicileri 1997- 2000, BDDK Mali Sektör Politikaları Dairesi, Çalışma Raporları, No: 2002/1.
• Kumar, P.R. ve Ravi, V..(2007). Bankruptcy Prediction in Banks and Firms via Sta- tistical and Intelligent Techniques. European Journal of Operational Research, 180(1): 1–28.
• Lavanya, V. ve Parveentaj, M..(2013). Foreign Currency Exchange Rate (FOREX) Using Neural Network. International Journal of Science and Research, 2(10): 174-177.
• Makeig, S., Jung, T.P. ve Sejnowski, T.J..(1996). Using Feedforward Neural Networks to Monitor Alertness from Changes in EEG Correlation and Coher- ence. Advances in neural information processing systems, Cambridge: MIT Press, 931–937.
• Mamatzakis, E.C. ve Remoundos, P.C..(2003). Determinants of Greek Commer- cial Banks Profitability, 1989 – 2000. SPOUDAI, 53(1): 84-94.
• Olson, D. ve Zobuni, T..(2011). Efficiency and Bank Profitability in MENA Coun- tries. Emerging Markets Review, 12: 104-110.
• Ozkan, C., Ozturk, C., Sunar, F. ve Karaboga, D..(2011). The Artificial Bee Colo- ny Algorithm in Training Artificial Neural Network for Oil Spill Detection. Neural Network World, 21:473-492.
• Öztemel, E..(2012). Yapay Sinir Ağları. İstanbul: Papatya Yayıncılık.
• Parasız, İ..(2013). Para Banka ve Finansal Piyasalar. Bursa: Ezgi Kitabevi Yayınları.
• Pasiouras, F. ve Kosmidou, K..(2007). Factors Influencing the Profitability of Do- mestic and Foreign Commercial Banks in the European Union. Research in Inter- national Business and Finance, 21: 222-237.
• Qiuhong, S. ve Jian, G..(2013). Specific Performance Prediction Based On BP Neural Network. International Journal of Digital Content Technology and its Ap- plications, 7(6): 514-521.
• Ravi, V. ve Zimmermann, H.J..(2001). A Neural Network and Fuzzy Rule Base Hybrid for Pattern Classification. Soft Computing, 5(2): 152–159.
• Saeed, M.S..(2014). Bank-related, Industry-related and Macroeconomic Factors Affecting Bank Profitability: A Case of the United Kingdom. Research Journal of Finance and Accounting , 5(2): 42-50.
• Saunders, A. ve Schumacher, L..(2000). The Determinants of Bank Interest Rate Margins: An International Study. Journal of International Money and Finance, 19(6): 813-832.
• Sayılgan, G. ve Yıldırım, O..(2009). Determinants of Profitability in Turkish Ban- king Sector: 2002-2007. International Research Journal of Finance and Econo- mics, 28: 207-213.
• Sheela, K.G. ve Deepa, S.N..(2013). Review on Methods to Fix Number of Hidden Neurons in Neural Networks. Mathematical Problems in Engineering, doi:10.1155/2013/425740.
• Singh, K.K., Pal, M. ve Singh, V.P..(2010). Estimation of Mean Annual Flood in Indian Catchments Using Backpropagation Neural Network and M5 Model Tree. Water Resour Manage, 24 (10): 2007-2019.
• Srinivasa, K.G., Sridharan, K., Shenoy, P.D., Venugopal, K.R. ve Patnaik, L.M.. (2004). EASOM: An Efficient Soft Computing Method For Predicting The Share Values. Proceedings of IASTED International Conference on Artificial Intelligence and Applications, Innsburg, Avusturya, 264–269.
• Trujillo-Ponce, A..(2013). What Determines the Profitability of Banks? Evidence from Spain. Accounting & Finance, 53(2): 561-586.
• Tunay, K.B. ve Silpagar, A.M..(2006). Türk Ticari Bankacılık Sektöründe Karlılığa Dayalı Performans Analizi - I. TBB Araştırma Tebliğleri Serisi, No: 2006-01.
• Washington, S. Karlaftis, M. ve Mannering, F..(2011). Statistical and Economet- ric Methods for Transportation Data Analysis - 2nd Edition. Boca Raton, FL: Chapman and Hall/CRC.
• Yıldız, B. ve Akkoç, S..(2009). Banka Finansal Başarısızlıklarının Sinirsel Bulanık Ağ Yöntemi ile Öngörüsü. BDDK Bankacılık ve Finansal Piyasalar, 3(1): 9-36.
• Zadeh, L.A..(1994). The Roles of Fuzzy Logic and Soft Computing in the Con- ception, Design and Deployment of Intelligent Systems. BT Technology Journal, 14(4): 32-36.