Pricing Brazilian exchange rate options using an adaptive network-based fuzzy inference system

Abstract

Recently, option pricing has become the focus of risk managers, policymakers, traders and more generally all market participants, since they find valuable information in these contracts. This paper suggests the pricing performance evaluation on Brazilian exchange rate R$ (Reais) per US$ (U.S. Dollar) option contracts, traded at the Brazilian derivatives market, using an adaptive network-based fuzzy inference system, for the period from April 1999 to April 2009. A fuzzy rule-based system was built with a family of conditional if-then statements whose consequent are functions of the antecedents, and then composed with the aid of fuzzy neurons. The ANFIS model was compared against the Black closed-form formula and some neural networks topologies, considering traditional error measures and statistical tests. The results showed that the ANFIS model outperforms closed-form formula methodology in pricing Brazilian currency options, mainly for out-of-the money contracts.