Connectionist decision support system for international currency option trading

Abstract

Everyday, the international currency market weathers all forms of worldwide current affairs and governmental economics statistics releases. Such news may cause slight ripples on the exchange rate, or they may blow up extensive fluctuations in demands and supplies for major currencies. In order to gain from currency tradings, a trader has to gauge, and sometimes guess using gut feelings, the likely market movement, and act accordingly. In this paper, we present a neural-network based expert decision support system (EDSS) for assisting users in making currency option trading decisions. By utilizing neural network technology in its inference engine, the system is able to learn new knowledge through usage. In addition, the neural-network inference engine is able to perform fuzzy logic reasonings, and accept vague terms from the user inputs. Furthermore, it can change its reasoning strategy according to different users, thus realizing the idea of personalized logic system.