JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Kruger, JW
|
|
| dc.contributor.editor | Venter, L
|
|
| dc.contributor.editor | Lombard, R.R.
|
|
| dc.date.accessioned | 2018-09-10T13:01:22Z | |
| dc.date.available | 2018-09-10T13:01:22Z | |
| dc.date.issued | 2000 | |
| dc.identifier.citation | Kruger, J.W. (1997) Returns on the Stock Exchange. Proceedings of the 1997 National Research and Development Conference: Towards 2000, South African Institute of Computer Science and Information Technology), Riverside Sun, 13-14 November, 2000, edited by L.M. Venter and R.R. Lombard (PUCHEE, VTC) | en |
| dc.identifier.isbn | 1-86822-300-0 | |
| dc.identifier.uri | http://hdl.handle.net/10500/24823 | |
| dc.description.abstract | The McGreggor database supplies the accounting information of companies listed on the Johannesburg stock exchange. These attributes are not significantly correlated to the Return. The Pearl's algorithm in Bayesian belief networks induces a belief network from data. With a solid grounding in probability theory, the Pearl algorithm allows belief updating by propagating likelihoods of leaf nodes (variables) and the prior probabilities. The Pearl algorithm was originally developed for binary variables and my reseach was a generalization to more states. The data used to test this new method, in a Portfolio Management context, are the Return and various attributes of companies listed on the Johannesburg Stock Exchange (JSE). The results of this model was then compared to a Linear Regression model. The bayesian method performed much better than stepwise Linear Regression. | en |
| dc.language.iso | en | en |
| dc.title | Returns on the Stock Exchange | en |
