Using Genetic Algorithms and Neural Networks in Forecasting The Opening Cash Index: Evidence from the SGX-DT MSCI Taiwan Futures Index
| Autor: | Ching-Hua Chou, 周慶華 |
|---|---|
| Rok vydání: | 2001 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 89 This study investigates the information content of SGX-DT MSCI Taiwan futures prices during the non-cash-trading (NCT) period. The same day’s leading futures and previous day’s cash and futures market closing indices are first used to predict the opening cash price in the cash market by the back propagation neural network model. Sensitivity analysis is first employed to address and solve the issue of finding the appropriate setup of the networks topology. For searching the best parameter settings of neural network model, the integrated model in combining genetic algorithms and back propagation neural networks model is then constructed. To demonstrate the effectiveness of our proposed method, the five-minute intraday data of spot and futures index from October 1, 1998 to December 31, 2000 was evaluated using the designed neural network model. Analytic results demonstrate that the integrated model of genetic algorithms and neural networks outperforms the back propagation neural network model and the random walk model forecasts. Besides, the integrated model can successfully forecast whether the opening cash price index is up or down, in comparison with previous day’s cash closing index, in more than 80 percent of the testing sample. It therefore indicates that using appropriate model can extract valuable information involved in the futures prices during the NCT period in forecasting the opening cash price index. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|