透過您的圖書館登入
IP:3.128.199.210
  • 學位論文

結合技術指標與財經新聞之股票趨勢預測

Using Technical Indicators Combine Financial News for Stock Market Prediction

指導教授 : 邱志洲

摘要


股價的漲跌變化是許多投資人關心的議題,過去有許多研究用股票技術指標或單用文件探勘技術分析財經新聞預測股市收盤價,然而僅用技術指標預測股市趨勢時,技術指標無法對市場發出的訊息即時做趨勢修正;單方面分析財經新聞時會因為資料分析偏誤而造成預測結果的誤差。本研究結合股價技術指標分析的規則性買賣訊號及財經新聞專家對股市未來趨勢的觀點,以倒傳遞類神經網路預測股票未來的收盤價。實驗結果證明加入新聞預測指標的預測模式的確可較準確的預測股市收盤價。

並列摘要


To enhance the drawback that only using technical indicators to predict the trend of the stock market can’t immediately react with the important news release by the government, industry. Hence we not only use technical indicators but also add the stock financial judgments from the financial specialist who has a long term studies of the solar industry, tend to use their predictions and experiences of the future to help the stock predictions be more accurate. We put technical indicators, judgment by the financial specialist into artificial neural network trying to predict the close price of the stock market the next day. The experiment shows that add the financial judgment by the specialist could make result more accuracy. Besides, our prediction model can catch the trend when some severe fluctuation cause by the release of the important news.

參考文獻


[2] G. Salton, Automatic Text Processing: The Transformation, Analysis and Retrieval of Information by Computer, New York: Addision-Wesley,1989
[4] C. Blake and W. Pratt, "Better rules, fewer features: a semantic approach to selecting feature from text, Proceedings," IEEE International Conference on Data Mining, 2001, pp. 59-66.
[5] S. Farbrizio, "Machine Learning in Automated Text Categorization," ACM Computing Surveys, vol.34, no. 1, 2002, pp.1-47.
[7] E. S. Atlam, M. Fuketa, S. Kashiji, H. Nakata and J. Aoe, " A new method for construction filed association terms using co-occurrence words and declinable words information, " IEEE International Conference on Systems, Man and Cybernetics, vol. 4, 2002, pp. 1217-1224.
[9] L. Anthony, " Characteristic features of research article titles in computer science, " IEEE Transactions on Professional Communication, Vol. 44, 2001, pp. 187-194.

被引用紀錄


蕭逢均(2017)。基於知識本體之企業價值的變化-以財經新聞為例〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2017.00056

延伸閱讀