A Study of Applying Genetic Algorithm to Exchange Rate Forecasting
碩士 === 國立臺北大學 === 統計學系 === 91 === This paper is the first research for using genetic algorithm in exchange rate forecasting in Taiwan. The purpose of the paper is to build a multiple regression model by using genetic algorithm and multiple interval rolling regression method. The first ste...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2003
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/93406149510508243137 |
| Summary: | 碩士 === 國立臺北大學 === 統計學系 === 91 === This paper is the first research for using genetic algorithm in exchange rate forecasting in Taiwan. The purpose of the paper is to build a multiple regression model by using genetic algorithm and multiple interval rolling regression method.
The first step is to transfer exchange rate price data to fifteen technical indicators. Each technical indicator has 10 types of parameters.
The second step is to choose from one hundrand fifty independent variables a linear combination of ten independent variables which have the best fitness function value in sample by using genetic algorithm .
The Final step is to build a multiple regression model with the ten independent variables which have the best fitness function value in sample to make a sample dynamic prediction by using multiple interval rolling regression method.
|
|---|