結合經驗模態分解法與自我迴歸移動平均於股價預測之應用

CCUR > College of Business > Department of Accounting & Graduate Institute of Accounting > Thesis > Item 987654321/20270

Please use this identifier to cite or link to this item: https://irlib.pccu.edu.tw/handle/987654321/20270

Title:	結合經驗模態分解法與自我迴歸移動平均於股價預測之應用
Authors:	郭定峪
Contributors:	會計學系
Keywords:	經驗模態分解法自我迴歸移動平均類神經網路
Date:	2010
Issue Date:	2011-11-07 14:53:21 (UTC+8)
Abstract:	本研究結合經驗模態分解法(empirical mode decomposition, EMD)及自我迴歸移動平均(auto regressive integrated moving aver-age, ARIMA)，藉由經驗模態分解法將資料分解為數個本質模態函數，以一天預測一天的方式與自我迴歸移動平均結合，分析股價的時間序列資料；由於台灣的股價變動有漲跌幅限制，使得股價只能在於有限的幅度中改變，因此股價間有很強的相關性，前一期的股價能解釋大部分的本期股價，本研究提出新的方法分析訊號，預測的結果可以做為未來估算股價的依據。研究結果顯示，對於股價的預測ARIMA優於類神經網路，EMD可有效改善ARIMA與類神經網路預測之準確性，二研究方法結合使用，會較單一模型更為準確。 The combination of empirical mode decomposition and autoregressive moving average, and by empirical mode decomposition data decomposition into several intrinsic mode functions, one way to predict the day and the autoregressive moving average combination of time series analysis of stock price information; because there are changes in Taiwan's stock price limits, causing the share price is limited only to change the rate, so stock prices have a strong correlation between the former shares one can explain most of the current stock price, this study new method of signal, the predicted results can be used as the basis for estimated future stock price. The results show that the forecast for the stock price is better than ARIMA neural network, EMD can effectively improve the ARIMA and neural network prediction accuracy, two methods in combination, would be more accurate than a single model.
Appears in Collections:	[Department of Accounting & Graduate Institute of Accounting] Thesis

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	319	View/Open

Loading...