透過您的圖書館登入
IP:3.137.192.3
  • 學位論文

叢集式類神經網路在股價轉折點預測之應用

Using Ensemble Neural Network on Stock Turning Points’ Prediction

指導教授 : 張百棧

摘要


一直以來股市就是最為普遍的一種投資方式,本研究最終目的是建立一個高效率的股市決策支援系統,希望藉由此一系統可以提供投資者額外的參考,對於投資人來說,有很多保守的散戶是將股票作為一長期投資,只希望可以得到穩定的投資報酬率。本研究主要利用線段切割法(Picewise Linear Representation–PLR)和叢集式類神經網路(Ensemble Neural Network)來進行股票轉折點之預測。線段切割法主要應用在將股價資料做細部線段切割,並且去除雜訊資料,以判斷股價走勢,如何決定細部線段切割之最佳門檻值為一重要關鍵;而叢集式類神經網路主要是結合多個不同的類神經網路,透過此一方法讓最後的輸出可以穩定,以達到投資人希望穩定報酬率的目標。 因此,本研究利用線段切割法(PLR)結合叢集式類神經網路,透過建構線段切割法結合叢集式類神經網路,形成一股市交易決策支援系統,為投資人提供一個明確的投資考量指標,以選擇買賣股票的適當時機,有效的降低投資風險,及提高投資報酬率。 其中,類神經網路主要在訓練技術指標(Input Variables)與股價轉折點(Output Variables)之連結權重,透過叢集式方法期望找出穩定的最佳買賣點時機。本研究以台灣股市與美國股市中的個股作為研究對象,將以預測出的買賣點進行實際的投資獲利計算,經實驗結果證明,本研究所建構之線段切割法及叢集式類神經網路之預測模型,比傳統之技術指標方法能更加準確且穩定的預測出股價之最佳轉折點。

並列摘要


Stock market has been the most common way of an investment, this research try to establish an efficient decision-making system of the stock market, through this system can help investor getting steady investment profit. In this research, Ensemble Neural Network system with Intelligent Piecewise Linear Representation for stock turning points detection is presented. The Intelligent piecewise linear representation method is able to generate numerous stocks turning signals from the historic data base, then Ensemble Neural Network system will be applied to train the pattern and retrieve similar stock price patterns from historic data for training. These turning signals represent short-term and long-term trading signals for selling or buying stocks from the market which are applied to forecast the future turning points from the set of test data. Experimental results demonstrate that the hybrid system including Taiwan and USA stocks that can make a significant and constant amount of profit when compared with other approaches using stock data available in the market.

並列關鍵字

PLR Ensemble Neural Network

參考文獻


67. 賴鍵元,「軟性計算於商品管理之應用」,元智大學工業工程與管理學系,2006年博士論文。
1. Agrawal, R. and R. Srikant, “Fast Algorithm for Mining Association Rules in Large Databases, ”Proc.20th Very Large Database Conf.,pp.478-499, Sept.,1994.
2. Arifovic, J. R. Gencay, “ Using genetic algorithms to select architecture of a feedback artificial neural network,” Physica, Vol. A, pp.574-594, 2001.
4. Bjorn, V., “Multiresolution methods for financial time series prediction, ”Computational Intelligence for Financial Engineering,Proceedings of the IEEE/IAFE,pp.97.1995.
6. Chen, T., “A Fuzzy Back Propagation Network for Output Time Prediction in a Wafer Fab,” Applied Soft Computing 2/3F, pp.211-222, 2003.

被引用紀錄


黃鉦皓(2013)。股市關鍵技術指標萃取於智慧型交易系統之研究〔碩士論文,元智大學〕。華藝線上圖書館。https://doi.org/10.6838/YZU.2013.00102
潘伊芳(2012)。建構趨勢切割法與支撐向量迴歸於股票買賣時機之預測〔碩士論文,元智大學〕。華藝線上圖書館。https://doi.org/10.6838/YZU.2012.00088
張凱婷(2011)。應用支撐向量迴歸及模糊規則於股價買賣點之預測〔碩士論文,元智大學〕。華藝線上圖書館。https://doi.org/10.6838/YZU.2011.00108

延伸閱讀