A study of Trading Strategies of TAIEX Futures by using EEMD-based Neural Network Learning Paradigms

• Main Authors: Chen,Yuan Hsiao, 陳原孝
• Other Authors: 蕭又新
• Format: Others
• Language: zh-TW
• Online Access: http://ndltd.ncl.edu.tw/handle/45517817831628921875

碩士 === 國立政治大學 === 應用物理研究所 === 101 === Financial market changes constantly and Stock Price Volatility (SPV) seems to be no significant rules. This means behavioral characteristic of the stock price cannot foresee and uncertain accurately. In order to increase revenue and reduce investment risk in the market, researchers had to try to establish an effective prediction model of financial markets. It can estimate the impact of this uncertainty. It's a great pity that there is not a model that is close successfully yet. That does not represent it does not exist successful model. Instead, researchers need to establish more predictive models to offer the market to judge the rule of thumb. The forecasting results of TAIEX Index futures by ARMA Model and two types of EEMD-ANN Models were compared in two kinds of markets – trend and fluctuation. In addition, two trading strategies were tested after the future prices are forecasted. The study attempted to identify a suitable forecasting model. Moreover, the factors for price fluctuation of TAIEX were also analyzed in the study. Through EEMD, they could be decomposed to IMFs with various physical meanings and more important IMFs were selected to be analyzed in accordance with the statistic value.