The Predictive Success and Profitability of Chart Patterns: Application to the Euro/Dollar Foreign Exchange Market

Abstract:     
In this paper, we investigate the existence of chart patterns in the euro/dollar intradaily foreign exchange market. We use two methods to identify the sequence of extrema forming different chart patterns, we develop twelve algorithm for patterns recognition and we study the detected chart patterns through two criteria: predictability and profitability. We run a Monte Carlo simulation to compute the statistical significance for the obtained results. We find an apparent existence of some chart patterns in the currency market. We show that more than one half of detected charts present a significant predictability. However, only two charts from our sample of twelve involve a significant profitability which is too small and fails to cover the transaction costs. We show, in addition, that the extrema detection method based on both High and Low prices (M2) provides higher but more risky profits that the method built on only the close prices (M1).

Keywords: foreign exchange market, technical patterns, high frequency data

JEL Classifications: C13, C14, F31

Working Paper Series