Abstract
A new stock price prediction model is proposed based on Genetic Network Programming (GNP), i.e., an evolutionary computation recently developed. In the proposed prediction model, GNP is applied to searching for an optimal combination of two or more appropriate stock price indices, which is different from a conventional GA or GP based stock price prediction model, where GA or GP is usually used as an optimization technique to search for an optimal value of parameters in the stock price index. In this paper, a combination of several indices is shown to be more effective than a single index, because the most effective index usually differs from one brand to another. A series of simulation studies are carried out to confirm the effectiveness of the proposed new model.
Original language | English |
---|---|
Pages | 1477-1482 |
Number of pages | 6 |
Publication status | Published - 2004 Dec 1 |
Event | SICE Annual Conference 2004 - Sapporo, Japan Duration: 2004 Aug 4 → 2004 Aug 6 |
Conference
Conference | SICE Annual Conference 2004 |
---|---|
Country | Japan |
City | Sapporo |
Period | 04/8/4 → 04/8/6 |
ASJC Scopus subject areas
- Control and Systems Engineering
- Computer Science Applications
- Electrical and Electronic Engineering