American Option Pricing Using Computational Intelligence Methods
| dc.contributor.author | Pires, Michael Maio | |
| dc.date.accessioned | 2006-03-22T10:44:49Z | |
| dc.date.available | 2006-03-22T10:44:49Z | |
| dc.date.issued | 2006-03-22 | |
| dc.description | Master of Science in Engineering - Engineering | en |
| dc.description.abstract | An option is the right to buy or sell an underlying asset at a future date by fixing the price now. The field of option pricing produces a challenge because of the complexity with pricing American styled options which cannot be done by the Black-Scholes equations. Neural Networks and Machine Learning techniques are predictors based on past data and it is intuitive to believe that they can model American options as they are non-linear instruments. Call option data on the South African All Share Index (ALSI) was used for testing of the techniques. These two different techniques were compared. What was also done was the comparison of Bayesian techniques applied to both the techniques. What this provided was confidence levels for the predictions. The investigations showed that Machine Learning techniques out-performed Neural Networks. The investigations also showed that there is scope for work to be done to improve the model. | en |
| dc.format.extent | 678687 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/10539/268 | |
| dc.language.iso | en | |
| dc.subject | computational | en |
| dc.subject | pricing | en |
| dc.subject | american | en |
| dc.title | American Option Pricing Using Computational Intelligence Methods | en |
| dc.type | Thesis | en |