透過您的圖書館登入
IP:3.236.111.234
  • 學位論文

開發一混合系統於股價與交易點之預測

Develop a Hybrid System for Stock Price and Trading Points Prediction

指導教授 : 張百棧

摘要


股市交易向來是全球投資人注目的焦點,股票、期貨與基金皆是投資人可以選擇的標的,如何建立一套有效的決策支援系統以供股價預測將是一項重要的課題。若系統能建立完善,投資者將可賺取更多利潤。在股市預測這個研究領域上主要分為兩個課題–股價預測與交易點預測。目前已有許多研究專研於股價預測,甚少有研究致力於交易點之預測。交易點之預測被許多學者評為隨機過程,預測正確率實在令人質疑。但是,若能透過本研究所提的混合系統作一適當預測,其預測將有優異之表現。本研究所提之混合系統包含三部份:(1) 資料前處理;(2) 演化預測過程;(3) 最終決策階段。在資料前處理階段裡,股票篩選、因子選擇、資料分群、資料模糊化都是必要的處理過程。由於股價預測與交易點預測是兩個完全不同的問題,所以適用的預測模式也不同。本研究將採納近年來所發展的軟性計算方法做為預測模式之核心。Takagi-Sugeno-Kang (TSK)將用來預測股價;於交易點預測則選擇Case Based Reasoning (CBR)、Back-Propagation Network (BPN)與Piece-wise Linear Represent (PLR)。儘管因應不同問題所使用的預測方法不同,這些方法都會面臨參數最佳化的過程,演化式演算法將扮演這個最佳化的角色。在最後,預測結果將會與近年來的混合模式作一比較。不論探討的是股價或是交易點預測,本研究所提的混合系統皆有不錯的表現。其最主要之貢獻在於交易點之預測,本論文提供了另一個自主式決定交易點之方法–EPLR,其投資報酬率高達123%,該結果相較於大多數的投資基金優異甚多。

並列摘要


The stock market has become the main outlet for investment recently in the world. The futures indicator, investment foundations, foreign capitals are diverse choices for investors. Investors may earn more money form the stock market by adopting a good forecasting system. When considering the stock market forecasting problem, two main topics need to be focused: stock price prediction and trading point prediction. Many studies are focused on the first topic, stock price prediction; but few of them are focused on trading point prediction. Because trading points prediction is like a random walk. Many studies try to use pattern matching methods to forecast the future trends, but they only can do the long trend forecasting. In this thesis, an efficiently hybrid forecasting system will be developed for be a short trend forecaster in this study. The hybrid system concludes three parts: (1) data preprocessing, (2) evolutionary forecasting method, (3) final decision making. In the first part, stock screening, feature selection, and data clustering are the necessary procedures. In the second part, stock price prediction and trading point prediction are different research fields, dissimilar Soft Computing methods will be adopted. Takagi-Sugeno-Kang (TSK) model will be adopted to predict the stock price; Case Based Reasoning (CBR), Back-Propagation Network (BPN), and Piece-wise Linear Represent (PLR) will be used to judge the trading points. All forecasting models have a lot parameters need to be calibrated. Considering the different solution spaces and problem complexities, evolutionary algorithms will be adopted to find the best parameters in the forecasting models. In the last, the final trading decision will be generated to compare some recent studies with the same conditions. No matter which topic we selected, this hybrid system developed in this study performs better. In stock price prediction, the forecasting error is less than 0.05%; in trading points prediction, the rate of return is greater than 123% in those target stocks.

參考文獻


[1] Bao, D.P., Yang, Z.H. (2008). Intelligent stock trading system by trading point confirming and probabilistic reasoning. Expert Systems with Applications, 34, pp.620-627.
[2] Aiken, M., Bsat, M. (1999). Forecasting Market Trends with Neural Networks. Information Systems Management, 16, pp.42-48.
[3] Chang, P.C., Wang, Y.W., Yang, W.N. (2004). An Investigation of the Hybrid Forecasting Models for Stock Price Variation in Taiwan. Journal of the Chinese Institute of Industrial Engineering, 21, pp.358-368.
[4] Pesaran, H.M., Timmermann, A. (1994). Forecasting stock returns: an examination of stock market trading in the presence of transaction costs. Journal of Forecasting, 13, pp.335-367.
[5] Haykin, S. (1998). Neural Networks: a Comprehensive Foundation, second ed. Prentice-Hall, Englewood Cliffs, NJ.

延伸閱讀