A cerebellar associative memory approach to option pricing and arbitrage trading

Abstract

Option pricing is a process to obtain the theoretical fair value of an option based on the factors affecting its price. The classical approaches to option pricing include the Black–Scholes pricing formula and the binomial pricing model. These techniques, however, employ complex and rigid statistical formulations that are not easily comprehensible to novice investors. More recently, non-parametric and computational methods of option valuation that are able to construct a model of the pricing formula from historical data have been proposed in the literature. However, most of these models functioned as black-boxes and may not be able to efficiently and accurately capture the complex market dynamics and characteristics of the option data. This paper proposes a novel brain-inspired cerebellar associative memory model for pricing American-style call options on British pound vs. US dollar currency futures. The proposed model, named PSECMAC, constitutes a local learning model that is inspired by the neurophysiological aspects of the human cerebellum. The PSECMAC-based option-pricing model is subsequently applied in a mis-priced option arbitrage trading system. Simulation results show an encouraging return on investment of 23.1% for some of the traded options.