International Journal of Computational Intelligence Research (IJCIR)

Volume 3, Number 1 (2007)


Exchange options pricing with evolutionary neural-based fuzzy inference systems

Hsing-Wen Wang
National Changhua University of Education, College of Management, Department of Business Administration, Changhua 500, Taiwan


The options markets and earlier studies take the Black-Scholes Generalized Model (BSG) as the practical model and develop more prospering. However, BSG is also based on many assumptions and constrains such that derivatives valuation with this model shows miss-pricing seriously, especially while compared with the market prices in foreign exchange options market. In order to overcome the drawbacks derived from BSG, we employ the proposed options pricing model through enhanced neural-fuzzy-based inference systems (ENFIS) in options pricing and then compared with the BSG. The evidence from empirical studies is using the euro foreign exchange options listed on the Chicago Mercantile Exchange (CME). The performance valuating comparisons were focused in the research period from 2002 to 2005. The results show that the ENFIS framework is superior to the BSG no matter in error degree or in the interpretation capability.

Black-Scholes generalized Model, enhanced neural-fuzzy-based inference systems, Genetic Algorithms, euro foreign exchange options, interpretation capability.