Decision support system for foreign exchange markets

Abstract

Selection of the right decision strategy is a crucial factor to success in the foreign exchange market. This article presents an innovative approach how to support related decision steps by means of suitable data mining methods applied on collected data from the market. The motivation is a trading under the best conditions, i.e. with the highest chance to be successful. To meet this requirement, we designed and implemented a decision support system (DSS) for trading on the foreign exchange market which uses a possibility to speculate on this market and in line with extracted rules, economic news and outputs of the technical analysis recommend the future trading direction. We extracted the rules from the historical Forex data with the C5.0 and CART algorithms for decision trees generation. The best achieved accuracy was 56.03% that is typical for this type of data. We used the best rules to design a dynamic trading strategy, which we experimentally verified as profitable.