簡易檢索 / 詳目顯示

回結果列表
研究生： 王邵雯
Wang, Shao-Wen
論文名稱： 以長短期記憶神經網路建構台股之長期投資策略
Development of Long-term Investment Strategies in Taiwan Stock Market by Using Long Short-Term Memory Neural Network
指導教授： 張焯然
Chang, Jow-Ran
口試委員: 劉鋼
Liu, Kang
蔡璧徽
Tsai, Bi-Huei
學位類別： 碩士
Master
系所名稱： 科技管理學院 - 計量財務金融學系
Department of Quantitative Finance
論文出版年： 2020
畢業學年度： 108
語文別： 中文
論文頁數： 48
中文關鍵詞： 長短期記憶神經網路 、深度學習 、財務比率 、公司價值
外文關鍵詞： Long short-term memory neural network, Deep learning, Financial ratio, Firm value
相關次數： 點閱：3  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

    • 　　在股票市場中，基本面、技術面及籌碼面是三大常見的投資分析工具，分別用來研究公司價值、判斷證券價值走勢及外資主力動向，現今AI人工智慧應用廣泛且滲透於我們的生活當中，從過去以機器學習預測股市的文獻中，多侷限於分析技術指標層面並建構短期投資策略，而我們期望以深度學習方法應用於長期投資策略，並考量投資新手在選股上的疑慮，提供給投資人方便快速的選股工具。
    　　本研究以臺灣所有上市公司為研究對象，利用16項基本面財務比率作為模型輸入變數，透過長短期記憶神經網路學習與未來一年公司價值成長率類別的關係，來預測公司價值未來成長趨勢，進而作為選股依據進行長期投資。實證結果顯示模型之整體預測成效不佳，但本研究在選股條件上設定嚴格，還是能夠篩選出公司價值有明顯變化之投資標的以戰勝大盤績效，提供給投資人具參考價值的投資建議。

    　　In the stock market, fundamental, technical, chip factors are three common investment analysis tools that are used to study the value of companies, determine the trend of securities value, and the main trend of foreign investment. Today, applications of artificial intelligence have widely penetrated into our lives. In the past, the literatures which used machine learning to predict the stock market were mostly limited to analyzing with technical indicators and constructing short-term investment strategies. We hope to construct long-term investment strategy by using deep learning method and take into account the doubts of stock selection in investors, in order to provide investors with a convenient and efficient stock selection tool.
    　　In this study, we take all listed companies in Taiwan as the research object. Learning the relationship between sixteen fundamental financial ratios and the classification of the firm’s value growth rate in the next year through long short-term memory (LSTM) neural network to do prediction, and then taking the results to construct long-term investment. Although the empirical results show that the performance of model prediction is not very well, due to the strict stock selection conditions, we still have abnormal return and provide investors with valuable recommendations.

    第一章、緒論----------1 第一節、研究背景與動機----------1 第二節、研究目的----------4 第三節、研究架構----------5 第二章、文獻回顧----------6 第三章、研究設計與方法----------8 第一節、研究方法----------8 第二節、模型變數----------15 第三節、研究流程與投資策略----------22 第四章、實證結果分析----------24 第一節、模型訓練結果----------24 第二節、投資績效分析----------31 第三節、個股分析----------37 第五章、結論----------45 參考文獻----------47

    1. 李麗滿（民國109年3月27日）。嘉威出運 去年Q4 EPS近3元創高。工商時報。取自https://ctee.com.tw/news/stock/243149.html

    2. 鄭淑芳（民國108年11月07日）。新鉅科三引擎熱 明年再成長。中時電子報。取自https://www.chinatimes.com/newspapers/20191107000360-260204?chdtv

    3. Akita, R., Yoshihara, A., Matsubara, T., & Uehara, K. (2016). Deep learning for stock prediction using numerical and textual information. In Computer and Information Science (ICIS), 2016 IEEE/ACIS 15th International Conference on (pp. 1-6). IEEE.

    4. Ariyo, A. A., Adewumi, A. O., & Ayo, C. K. (2014). Stock price prediction using the ARIMA model. In Computer Modelling and Simulation, 2014 UKSim-AMSS 16th International Conference on (pp. 106-112). IEEE.

    5. Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE transactions on neural networks, 5(2), 157-166.

    6. Chen, A. S., Leung, M. T., & Daouk, H. (2003). Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index. Computers & Operations Research, 30(6), 901-923.

    7. Dutta, A., Bandopadhyay, G., & Sengupta, S. (2012). Prediction of stock performance in indian stock market using logistic regression. International Journal of Business and Information, 7(1).

    8. Hassan, M. R., & Nath, B. (2005). Stock market forecasting using hidden Markov model: a new approach. In 5th International Conference on Intelligent Systems Design and Applications (ISDA'05) (pp. 192-196). IEEE.

    9. Hochreiter, S. (1991). Untersuchungen zu dynamischen neuronalen Netzen. Diploma, Technische Universität München, 91(1).

    10. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.

    11. Kara, Y., Boyacioglu, M. A., & Baykan, Ö. K. (2011). Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange. Expert systems with Applications, 38(5), 5311-5319.

    12. Katherine Lynch, Tom Lauricella. (2020, Jan 15). 2019 Fund Flows in 9 Charts. Retrieved from https://www.morningstar.com/articles/961935/2019-fund-flows-in-9-charts

    13. Nelson, D. M., Pereira, A. C., & de Oliveira, R. A. (2017). Stock market's price movement prediction with LSTM neural networks. In 2017 International joint conference on neural networks (IJCNN) (pp. 1419-1426). IEEE.

    14. Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications, 42(4), 2162-2172.

    15. Ruback, R. S., & Jensen, M. C. (1983). The market for corporate control: The scientific evidence. Journal of Financial economics, 11, 5-50.

    16. Shleifer, A., & Vishny, R. W. (1986). Large shareholders and corporate control. Journal of political economy, 94(3, Part 1), 461-488.

    17. Yao, J., Tan, C. L., & Poh, H. L. (1999). Neural networks for technical analysis: a study on KLCI. International journal of theoretical and applied finance, 2(02), 221-241.

    18. Yermack, D. (1996). Higher market valuation of companies with a small board of directors. Journal of financial economics, 40(2), 185-211.

    QR CODE