簡易檢索 / 詳目顯示

回結果列表
研究生： 洪煒翔
Hung, Wei-Hsiang
論文名稱： 採用機器學習模型分析搜尋聲量與股價相關性及可預測性－以高端疫苗為例
Analysis the correlation and prediction possibility between search volume and stock price for Medigen Vaccine Biologic Corporation by machine learning model
指導教授： 林哲群
Lin, Che-Chun
口試委員: 楊屯山
Yang, Twan-Shan
張焯然
Chang, Jow-Ran
學位類別： 碩士
Master
系所名稱： 科技管理學院 - 國際專業管理碩士班
International Master of Business Administration(IMBA)
論文出版年： 2022
畢業學年度： 110
語文別： 英文
論文頁數： 45
中文關鍵詞： 機器學習 、股價預測 、財務行為學 、Google搜尋趨勢 、高端疫苗
外文關鍵詞： Machine Learning, Stock Price Preidiction, Behavioral Finance, Google Trend, Medigen
相關次數： 點閱：2  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 在此篇研究中，採用了Google Trends搜尋聲量於2021的統計資料以及高端疫苗(MVC: 6547)於2021年的股價資料進行分析研究。目的為透過過去的搜尋聲量，預測未來的股價趨勢。未來的指標在過去研究中已被證明可以做為推論過去股價的標的，但過去的指標則會有較大的偏差。本研究中採用RapidMiner的內建六組模型進行機器學習分析，以過去、未來及移動平均因子分析股價預測的可行性。研究組別中，分為五組不同因子組合，主要區分方法為過去因子、未來因子及過去移動平均因子。並在當中發現移動平均因子搭配隨機森林模型對於股價預測的效率最佳，預測股價與實際股價的相關係數高達0.933並且僅有6.8%的誤差值。研究結果也顯示Google Trends搜尋聲量有潛力可做為直接或間接預測股價的指標。

    The stock price data of Medigen Biologics Vaccine Corporation (MVC: 6547) in 2021 and the statistics of Google Trends' search traffic in 2021 are used for analysis and research in this study. The goal is to forecast future stock price trends based on previous search volume. Future indicators have been shown to be the aim of inferring past stock values in previous study, however past indicators will have larger variations. RapidMiner's built-in six models are utilized for machine learning analysis in this study to assess the feasibility of stock price predictions using past, future, and moving average parameters. Past factor, future factor, and past moving average factor are the key distinguishing approaches in the research group, which is separated into five groups of different factor combinations. The moving average component in combination with the random forest model is shown to be the most effective for stock price prediction. The correlation coefficient between the anticipated and actual stock prices is as high as 0.933, with an error value of only 6.8%. The findings also suggest that Google Trends search traffic might be used to anticipate stock values, either directly or indirectly.

    摘要 I Abstract II Chapter 1: Introduction 1 1.1 Research Background and Motivation 1 1.2 Research Questions 2 Chapter 2: Literature Review 3 2.1 Introduction to Medigen Vaccine Corp. 3 2.2 Introduction to Google Trends 4 2.3 Introduction to Machine Learning 5 2.4 Random Walk Hypothesis and Non-Random Walk Hypothesis 7 2.5 Past Studies about Stock Price and Attention Theory 8 Chapter 3: Research Methodology 11 3.1 Data Collection 11 3.2 Descriptive Statistics 12 Chapter 4: Finding and Analysis 16 4.1 Correlation Analysis 16 4.2 Machine Learning Model and Analysis Result 17 4.3 Limitation 41 Chapter 5: Conclusion 42 5.1 Conclusion 42 5.2 Future Study and Advise 43 Reference 44

    1. Li, Y., Tu, Y., & Wang, W. (2017). Google Search Volume Index and Its Effects on Stock Return and Trading Volume of Taiwan Stock Market. Journal of Management and System, 24(4), 565–590.
    2. Regnault, J. A. frédéric. (1863). Calcul Des Chances et Philosophie de La Bourse. Paris : Mallet-Bachelier [et] Castel.
    3. Bachelier, L. J. alphonse. (1900). The Theory of Speculation. Annales Scientifiques de l’Ecole Normale Sup ´ Erieure ´ , Ser., 3(17), 21–86.
    4. Cootner, P. H. (1967). The Random Character of Stock Market Prices. The MIT Press.
    5. Defusco, R. A., Mcleavey, D. W., Pinto, J. E., & Runkle, D. E. (2015). Quantitative Investment Analysis (3rd ed.). Wisley.
    6. Fromlet, H. (2001). Behavioral Finance-Theory and Practical Application: SYSTEMATIC ANALYSIS OF DEPARTURES FROM THE HOMO OECONOMICUS PARADIGM ARE ESSENTIAL FOR REALISTIC FINANCIAL RESEARCH AND ANALYSIS. Business Economics, 36(3), 63–69.
    7. Bank, M., Larch, M. and Peter, G. (2011). Google Search Volume and Its Influence on Liquidity and Returns of German Stocks. Financial Markets and Portfolio Management, 25(3), 239-264.
    8. Huberman, G. and Regev T. (2001). Contagious Speculation and a Cure for Cancer: A Nonevent that Made Stock Prices Soar. Journal of Finance, 56(1), 387-396.
    9. Joseph, K., Wintoki, M. B., and Zhang, Z. (2011). Forecasting Abnormal Stock Returns and TradingVolume Using Investor Sentiment: Evidence from Online Search. International Journal of Forecasting, 27(4), 1116-1127.
    10. Takeda, F. and Yamazaki, H. (2006). Stock Price Reactions to Public TV Programs on Listed Japanese Companies. Economics Bulletin, 13(7), 1-7.
     
    11. Kim, Y. H. and Meschke, F. (2011) CEO Interviews on CNBC. Working Paper, Fifth Singapore International Conference on Finance 2011. available at SSRN:
    12. Vlastakis, N. and Markellos, R. N. (2012). Information Demand and Stock Market Volatility. Journal of Banking and Finance, 36(6), 1808-1821.
    13. About Us. (n.d.). Medigen Vaccine Biologics Corp. https://www.medigenvac.com/en/about.php
    14. 衛福部核准高端MVC-COV1901新冠肺炎疫苗專案製造. (2021, July 19). 衛生福利部. https://www.mohw.gov.tw/cp-5018-62288-1.html
    15. COVID-19公費疫苗預約平台增加開放35歲至20歲(含)民眾預約高端疫苗，於8月23日起施打. (2021, August 18). 衛生福利部. https://www.mohw.gov.tw/cp-5019-62802-1.html
    16. Trends Help. (n.d.). Google. https://support.google.com/trends/?hl=zh-Hant#topic=
    17. 證券櫃檯買賣中心. (n.d.). 證券櫃檯買賣中心. https://www.tpex.org.tw/web/index.php?l=zh-tw
    18. Google Trends. (n.d.). https://trends.google.com.tw/trends/?geo=TW
    19. COVID - Explore - Google Trends. (n.d.). Google Trends. https://trends.google.com/trends/explore?date=2021-01-01%202021-12-31&geo=TW&q=COVID
    20. 因應社區傳播有擴大趨勢，指揮中心自即日起至5月28日提升雙北地區疫情警戒至第三級，加嚴、加大全國相關限制措施，嚴守社區防線. (2021, May 15). 衛生福利部疾病管制署. https://www.cdc.gov.tw/Category/ListContent/EmXemht4IT-IRAPrAnyG9A?uaid=E7bi2j8UYj1Rmz73OPE7Yg
    21. 指揮中心自7月27日至8月9日調降疫情警戒標準至第二級，請民眾持續配合防疫措施，守護彼此健康. (2021, July 23). 衛生福利部疾病管制署. https://www.cdc.gov.tw/Category/ListContent/EmXemht4IT-IRAPrAnyG9A?uaid=e0v8zImE3rGJ0072A86NHA

    QR CODE