Oceňování opcí: Metodologická retrospektiva a empirické srovnání Black-Scholesova oceňovacího modelu a neuronových sítí

Vlasáková Baruníková, Michaela

Since the famous Black, Scholes, Merton formula substantial progress has been made in the option pricing theory. We recapitulate this development in the first part of the work to provide the reader with the comprehensive methodological review of the option pricing techniques and we describe the most common issues one has to deal with in empirical application. The aim of the empirical part is to evaluate the difference between the rather simple but revolutionary Black- Scholes model and one of the more complex techniques (neural networks) on the European-style S&P Index call and put options over the period of 1.6.2006 till 8.6.2007. Our results on call options show that generally Black-Scholes model with historical and at-the-money implied volatility performs better than simple generalized feed-forward networks. On the other hand neural networks performance is improving as the option goes deep in the money and as days to expiration increase, compared to the worsening performance of the BS models. Neural networks seem to correct for the well-known Black-Scholes model moneyness and maturity biases. All models have much lower explanatory power for put options compared to calls. Since options are real indicators of the market movements we assign this fact to the expectations of the market participants...

guest :: login Digital Repository
		Search		Submit		Help		About