American option pricing using bayesian multi-layer perceptrons and bayesian support vector machines

Michael M. Pires, Tshilidzi Marwala

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Citations (Scopus)

Abstract

An option is the right, not the obligation, to buy or sell an underlying asset at a later date but by fixing the price of the asset now. There are European and American styled options... European styled options can be priced using the Black-Scnoles equations but American options are more complex and valuable due to the second random process they introduce. Multi-Layer Perceptions and Support Vector Machines have been used previously to price American options and what is introduced here is Bayesian Techniques to both these approaches. Bayesian techniques used with both these approaches are compared in terms of pricing accuracy and time to train each of the learning algorithms. It was found that Bayesian SVM's out-performed Bayesian MLP's and that there is scope for further work. However, Bayesian SVM's took much longer to train than Bayesian MLP's even though they produced better error results.

Original languageEnglish
Title of host publicationICCC 2005 - IEEE 3rd International Conference on Computational Cybernetics - Proceedings
Pages219-224
Number of pages6
DOIs
Publication statusPublished - 2005
Externally publishedYes
EventICCC 2005 - IEEE 3rd International Conference on Computational Cybernetics - Mauritius, Mauritius
Duration: 13 Apr 200516 Apr 2005

Publication series

NameICCC 2005 - IEEE 3rd International Conference on Computational Cybernetics - Proceedings
Volume2005

Conference

ConferenceICCC 2005 - IEEE 3rd International Conference on Computational Cybernetics
Country/TerritoryMauritius
CityMauritius
Period13/04/0516/04/05

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'American option pricing using bayesian multi-layer perceptrons and bayesian support vector machines'. Together they form a unique fingerprint.

Cite this