Application of Neural Network and Simulation Modeling to Evaluate Russian Banks’ Performance

This paper presents an application of neural network and simulation modeling to analyze and predict the performance of 883 Russian Banks over the period 2000-2010. Correlation analysis was performed to obtain key financial indicators which reflect the leverage, liquidity, profitability and size of Banks. Neural network was trained over the entire dataset, and then simulation modeling was performed generating values which are distributed with Largest Extreme Value and Loglogistic distributions with estimated parameters providing robust results. Next, a combination of neural network and simulation modeling techniques was validated with the help of back-testing. Finally, we received nine bank clusters that describe the structural performance within the Russian Banking sector.

[1]  Constantin Zopounidis,et al.  A multicriteria decision framework for measuring banks' soundness around the world , 2006 .

[2]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[3]  Constantin Zopounidis,et al.  A multivariate analysis of the financial characteristics of foreign and domestic banks in the UK , 2006 .

[4]  Kuldeep Kumar,et al.  Forecasting credit ratings using an ANN and statistical techniques , 2003 .

[5]  Kok-Hui Tan,et al.  Stress testing using VaR approach—a case for Asian currencies , 2003 .

[6]  Mohamed M. Mostafa,et al.  Modeling the efficiency of top Arab banks: A DEA-neural network approach , 2009, Expert Syst. Appl..

[7]  M. Hassan,et al.  Efficiency, Ownership and Market Structure, Corporate Control and Governance in the Turkish Banking Industry , 2003 .

[8]  C. Ho,et al.  Benchmarking performance indicators for banks , 2006 .

[9]  Loretta J. Mester,et al.  Inside the Black Box: What Explains Differences in the Efficiencies of Financial Institutions? , 1997 .

[10]  Fotios Pasiouras,et al.  Assessing Bank Efficiency and Performance with Operational Research and Artificial Intelligence Techniques: A Survey , 2009, Eur. J. Oper. Res..

[11]  David E. Booth,et al.  The use of fuzzy clustering algorithm and self-organizing neural networks for identifying potentially failing banks: an experimental study , 2000 .

[12]  Vadlamani Ravi,et al.  Soft computing system for bank performance prediction , 2008, Appl. Soft Comput..

[13]  Robert Sollis.  Value at risk: a critical overview , 2009 .

[14]  Soushan Wu,et al.  Credit rating analysis with support vector machines and neural networks: a market comparative study , 2004, Decis. Support Syst..

[15]  Emmanuel Thanassoulis,et al.  Comparative efficiency analysis of Portuguese bank branches , 2007, Eur. J. Oper. Res..

[16]  Constantin Zopounidis,et al.  Assessing Bank Soundness with Classification Techniques , 2009 .

[17]  Victor C. Shih,et al.  Comparing the performance of Chinese banks: A principal component approach ☆ , 2007 .

[18]  Iftekhar Hasan,et al.  Bank performance, efficiency and ownership in transition countries , 2005 .

[19]  Miguel García-Cestona,et al.  Multiple goals and ownership structure: Effects on the performance of Spanish savings banks , 2008, Eur. J. Oper. Res..

[20]  A. Gnezditskaia.  Russian banks’ profit strategies: the evidence from various types of banks , 2003 .

[21]  Dennis Olson,et al.  Efficiency and bank profitability in MENA countries , 2011 .

[22]  Gleb Lanine,et al.  Failure prediction in the Russian bank sector with logit and trait recognition models , 2006, Expert Syst. Appl..

[23]  E. N. Ozkan-Gunay,et al.  Prediction of bank failures in emerging financial markets: an ANN approach , 2007 .

[24]  Panos M. Pardalos,et al.  A multicriteria approach for rating the credit risk of financial institutions , 2009, Comput. Manag. Sci..

[25]  Jan-Egbert Sturm,et al.  Foreign bank entry, deregulation and bank efficiency: Lessons from the Australian experience , 2004 .