Are emerging market currency crises predictable? A test

Arbeitspapier

This paper analyzes the predictability of emerging market currency crises by comparing the often used probit model to a new method, namely a multi-layer perceptron artificial neural network (ANN) model. According to the results, both models were able to signal currency crises reasonably well in-sample, but the forecasting power of these models out-ofsample was found to be rather poor. Only in the case of Russian (1998) crisis were both models able to signal the crisis well in advance. The results reinforced the view that developing a stable model that can predict or even explain currency crises is a challenging task.

Show object

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: ECB Working Paper ; No. 571

Classification and Topics

• Classification: Wirtschaft ; Foreign Exchange ; Financial Markets and the Macroeconomy ; Single Equation Models; Single Variables: Discrete Regression and Qualitative Choice Models; Discrete Regressors; Proportions; Probabilities ; Single Equation Models; Single Variables: Panel Data Models; Spatio-temporal Models ; Neural Networks and Related Topics
• Subject: artificial neural networks ; currency crises ; emerging markets ; Währungskrise ; Schwellenländer ; Prognose ; Neuronale Netze ; Künstliche Intelligenz ; Theorie ; Schwellenländer

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Peltonen, Tuomas A.
• Event: Veröffentlichung
• (who): European Central Bank (ECB)
• (where): Frankfurt a. M.
• (when): 2006

Further information

• Handle: http://hdl.handle.net/10419/153005