Pricing Chinese warrants using artificial neural networks coupled with Markov regime switching model Online publication date: Sat, 28-Feb-2015
by David Liu; Lei Zhang
International Journal of Financial Markets and Derivatives (IJFMD), Vol. 2, No. 4, 2011
Abstract: A non-parametric valuation framework (ANN-MRS) using artificial neural networks for pricing financial derivatives has been developed whilst the volatility of underlying asset return dynamics are modelled by Markov regime switching model. Its immediate application is on pricing of the Chinese warrants. To access the potential of neural network pricing with volatility in regime switching, weekly data of Jiangtong Stock returns are used to calculate the volatilities by using the maximum likelihood estimation. The ability of neural network for predicting the warrant prices is compared to the Black-Scholes model. Comparisons reveal that the mean squared error for the neural network is less than that of the Black-Scholes model in both in sample and out of sample estimations. The result indicates the neural network model coupled with Markov regime switching (for volatility estimation) has a superior performance comparing the warrant pricing by using the Black-Scholes model with historical volatility.
Online publication date: Sat, 28-Feb-2015
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Financial Markets and Derivatives (IJFMD):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email email@example.com