In search of a warning strategy against exchange-rate attacks: Forecasting tactics using artificial neural networks

摘要

“Heart attacks and devaluations are not predictable and, certainly, are never preannounced”. (The usual remark made by government spokesmen shortly after a domestic currency devaluation has taken place.)The contribution that this paper aspires to make is the prediction of an oncoming attack against the domestic currency, something that is expected to increase the possibilities of successful hedging by the authorities. The analysis has focused on the Greek Drachma, which has suffered a series of attacks during the past few years, thus offering a variety of such “shock” incidents accompanied by frequent interventions by the authorities. The prediction exercised here is performed in a discrete dynamics environment, based on the daily fluctuations of the interbank overnight interest rate, using artificial neural networks enhanced by genetic algorithms. The results obtained on the basis of the forecasting performance have been considered most encouraging, in providing a successful prediction of an oncoming attack against the domestic currency.