Developing an early warning system to predict currency crises

The purpose of this paper is to develop an early warning system to predict currency crises. In this study, a data set covering the period of January 1992–December 2011 of Turkish economy is used, and an early warning system is developed with artificial neural networks (ANN), decision trees, and logistic regression models. Financial Pressure Index (FPI) is an aggregated value, composed of the percentage changes in dollar exchange rate, gross foreign exchange reserves of the Central Bank, and overnight interest rate. In this study, FPI is the dependent variable, and thirty-two macroeconomic indicators are the independent variables. Three models, which are tested in Turkish crisis cases, have given clear signals that predicted the 1994 and 2001 crises 12months earlier. Considering all three prediction model results, Turkey’s economy is not expected to have a currency crisis (ceteris paribus) until the end of 2012. This study presents uniqueness in that decision support model developed in this study uses basic macroeconomic indicators to predict crises up to a year before they actually happened with an accuracy rate of approximately 95%. It also ranks the leading factors of currency crisis with regard to their importance in predicting the crisis.

[1]  David West,et al.  Neural network credit scoring models , 2000, Comput. Oper. Res..

[2]  Eric Séverin,et al.  Forecasting financial failure using a Kohonen map: A comparative study to improve model stability over time , 2012, Eur. J. Oper. Res..

[3]  César Hervás-Martínez,et al.  Income prediction in the agrarian sector using product unit neural networks , 2010, Eur. J. Oper. Res..

[4]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[5]  Andrew K. Rose,et al.  Currency crashes in emerging markets: An empirical treatment , 1996 .

[6]  Claustre Bajona,et al.  China's vulnerability to currency crisis: A KLR signals approach , 2008 .

[7]  Kin Keung Lai,et al.  A multiscale neural network learning paradigm for financial crisis forecasting , 2010, Neurocomputing.

[8]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[9]  Dursun Delen,et al.  A machine learning-based approach to prognostic analysis of thoracic transplantations , 2010, Artif. Intell. Medicine.

[10]  Marco Fioramanti,et al.  Predicting Sovereign Debt Crises Using Artificial Neural Networks: A Comparative Approach , 2006 .

[11]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[12]  Stefano Tarantola,et al.  Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models , 2004 .

[13]  Fabio H. Nieto,et al.  A note on linear combination of predictors , 2000 .

[14]  Tae Yoon Kim,et al.  Using Neural Networks to Support Early Warning System for Financial Crisis Forecasting , 2005, Australian Conference on Artificial Intelligence.

[15]  Steven B. Kamin,et al.  The Contributions of Domestic and External Factors to Latin American Devaluation Crises: An Early Warning Systems Approach , 1999 .

[16]  A. Rose,et al.  Contagion and Trade: Why Are Currency Crises Regional? , 1998 .

[17]  Carmen M. Reinhart,et al.  Leading Indicators of Currency Crises , 1997, SSRN Electronic Journal.

[18]  Dursun Delen,et al.  Predicting the graft survival for heart-lung transplantation patients: An integrated data mining methodology , 2009, Int. J. Medical Informatics.

[19]  GUOFANG NAN,et al.  Heuristic bivariate Forecasting Model of Multi-Attribute Fuzzy Time Series Based on Fuzzy Clustering , 2012, Int. J. Inf. Technol. Decis. Mak..

[20]  G. Kaminsky,et al.  Currency crises: Are they all the same?☆ , 2006 .

[21]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[22]  Bengi Kibritcioglu,et al.  A Leading Indicators Approach to the Predictability of Currency Crises: The Case of Turkey , 1999 .

[23]  Serpil Canbas,et al.  Prediction of commercial bank failure via multivariate statistical analysis of financial structures: The Turkish case , 2005, Eur. J. Oper. Res..

[24]  Carmen M. Reinhart,et al.  The Twin Crises: The Causes of Banking and Balance-of-Payments Problems , 1996 .

[25]  J. Armstrong,et al.  PRINCIPLES OF FORECASTING 1 Principles of Forecasting : A Handbook for Researchers and Practitioners , 2006 .

[26]  Andrew K. Rose,et al.  Exchange market mayhem: the antecedents and aftermath of speculative attacks , 1995 .

[27]  Michael Y. Hu,et al.  Artificial neural networks in bankruptcy prediction: General framework and cross-validation analysis , 1999, Eur. J. Oper. Res..

[28]  Andrew Berg,et al.  Predicting currency crises:: The indicators approach and an alternative , 1999 .

[29]  Jose C. Principe,et al.  Neural and adaptive systems , 2000 .

[30]  Sathāban Wičhai phư̄a Kānphatthanā Prathēt Thai.  EADN regional project on indicators and analyses of vulnerabilities to economic crises , 2003 .

[31]  Vijay S. Desai,et al.  A comparison of neural networks and linear scoring models in the credit union environment , 1996 .

[32]  Pranee Tinakorn.  Indicators and Analysis of Vulnerability to Currency Crisis: Thailand , 2006 .

[33]  Efstratios F. Georgopoulos,et al.  Forecasting foreign exchange rates with adaptive neural networks using radial-basis functions and Particle Swarm Optimization , 2013, Eur. J. Oper. Res..

[34]  A. Saltelli,et al.  Making best use of model evaluations to compute sensitivity indices , 2002 .

[35]  Toshiyuki Sueyoshi,et al.  DEA as a tool for bankruptcy assessment: A comparative study with logistic regression technique , 2009, Eur. J. Oper. Res..

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

[37]  A. Sanchis,et al.  Rough Sets and the role of the monetary policy in financial stability (macroeconomic problem) and the prediction of insolvency in insurance sector (microeconomic problem) , 2007, Eur. J. Oper. Res..

[38]  Paolo A. Pesenti,et al.  What Caused the Asian Currency and Financial Crisis , 1999 .

[39]  Soner Akkoç,et al.  An empirical comparison of conventional techniques, neural networks and the three stage hybrid Adaptive Neuro Fuzzy Inference System (ANFIS) model for credit scoring analysis: The case of Turkish credit card data , 2012, Eur. J. Oper. Res..

[40]  Vadlamani Ravi,et al.  Bankruptcy prediction in banks and firms via statistical and intelligent techniques - A review , 2007, Eur. J. Oper. Res..

[41]  Selim Zaim,et al.  A machine learning-based usability evaluation method for eLearning systems , 2013, Decis. Support Syst..

[42]  Charles W. Chase.  Composite Forecasting: Combining Forecasts for Improved Accuracy , 2000 .

[43]  E. Davis,et al.  Comparing early warning systems for banking crises , 2008 .

[44]  Roy Batchelor,et al.  Forecaster diversity and the benefits of combining forecasts , 1995 .

[45]  Tsung-Sheng Chang,et al.  A comparative study of artificial neural networks, and decision trees for digital game content stocks price prediction , 2011, Expert Syst. Appl..

[46]  I. Hasan,et al.  Financial Crises and Bank Failures: A Review of Prediction Methods , 2009 .

[47]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[48]  Pamela K. Coats,et al.  A neural network for classifying the financial health of a firm , 1995 .

[49]  Ruei-Yuan Chang,et al.  A New Approach to Modeling Early Warning Systems for Currency Crises : can a machine-learning fuzzy expert system predict the currency crises effectively? , 2006 .

[50]  Vadlamani Ravi,et al.  Cash demand forecasting in ATMs by clustering and neural networks , 2014, Eur. J. Oper. Res..

[51]  G. W. Davis,et al.  Sensitivity analysis in neural net solutions , 1989, IEEE Trans. Syst. Man Cybern..

[52]  Mario B. Lamberte,et al.  Monitoring economic vulnerability and performance : applications to the Philippines , 2001 .

[53]  Charles W. Chase.  Editorial: Understanding and Using the Power of Outliers in Statistical Modeling , 2001 .

[54]  M. Bussière,et al.  Towards a new early warning system of financial crises , 2002 .

[55]  Hali J. Edison,et al.  Do Indicators of Financial Crises Work? An Evaluation of an Early Warning System , 2000 .

[56]  Myung Suk Kim,et al.  Modeling special-day effects for forecasting intraday electricity demand , 2013, Eur. J. Oper. Res..

[57]  Dursun Delen,et al.  An analytic approach to better understanding and management of coronary surgeries , 2012, Decis. Support Syst..

[58]  Dursun Delen,et al.  Development of a structural equation modeling-based decision tree methodology for the analysis of lung transplantations , 2011, Decis. Support Syst..

[59]  Qing Cao,et al.  Forecasting wind speed with recurrent neural networks , 2012, Eur. J. Oper. Res..

[60]  Asil Oztekin,et al.  A decision support system for usability evaluation of web-based information systems , 2011, Expert Syst. Appl..