Technical trading rules in the European Monetary System

Using the genetic programming methodology developed in Neely, Weller and Dittmar (1997), we find trading rules that generate significant excess returns for three of four EMS exchange rates over the out-of-sample period 1986-1996. Permitting the rules to use information about the interest rate differential proved to be important. The reduction in volatility resulting from the imposition of a narrower band may reduce trading rule profitability. The currency for which there was least evidence of significant excess returns was the Dutch guilder, which was also the only currency that remained within a band of 2.25% throughout our sample period. Our results cannot be duplicated by the moving average or filter rules commonly used by technical analysts or by two trading rules designed specifically to exploit known features of target zone exchange rates. The observed excess returns cannot be explained as compensation for bearing systematic risk.