簡易檢索 / 詳目顯示
| 研究生： |
陳暐文 Chen, Wei-Wen |
|---|---|
| 論文名稱： |
利用深度學習圖形辨識技術建置最適投資策略-以台灣股票市場為例 Applying the Stock Chart Pattern Recognition with Deep Learning to Construct the Optimal Investment Strategy in Taiwan |
| 指導教授： |
黃泓智
Huang, Hong-Chih |
| 口試委員: |
楊曉文
Yang, Sharon S. 王昭文 Wang, Chou-Wen |
| 學位類別： |
碩士
Master |
| 系所名稱： |
商學院 - 風險管理與保險學系 Department of Risk Management and Insurance |
| 論文出版年： | 2019 |
| 畢業學年度： | 107 |
| 語文別： | 中文 |
| 論文頁數： | 50 |
| 中文關鍵詞： | 人工智慧 、深度學習 、自動編碼器 、多層感知機 、股票線圖 、台股 |
| 外文關鍵詞： | Stock charts, Multiple Layer Perception |
| DOI URL： | http://doi.org/10.6814/NCCU201901080 |
| 相關次數： | 點閱：163 下載：24 |
| 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 |
近年來，隨著電腦技術的革新，人工智慧在各領域皆有所突破。其中，圖像辨識可說是人工智慧運用的相當廣泛的一個領域，因此，本研究希望透過深度學習中圖像辨識相關技術，來預測股票線圖在未來的走勢，進一步選出預期報酬較高之股票作為投資組合。
本研究針對股票線圖一共進行兩階段處裡，第一階段採用自動編碼器（Autoencoder）技術，訓練出可將股票蠟燭圖、成交量圖降維之模型；第二階段則使用多層感知機(Multiple Perception Layer)模型對降為後資料進行學習，預測未來股票報酬率，建置投資組合。
最後，本文透過實證分析，回測模型績效，回測期間從2012至2019共8年，回測結果平均年化報酬率達22.69%，平均年化夏普比為1.49，明顯優於台灣加權指數表現。
In recent years, with the innovation of computer technology, artificial intelligence has made lots of breakthroughs in various fields. Among them, image recognition can be said to be a really successful one. Therefore, this paper hopes to predict the trend of stock charts through the image recognition skill in deep learning in order to construct the optimal portfolio.
This paper applies two models to predict stock charts. First, an AutoEncoder is used to reduce the candlesticks charts and volume charts from three dimensions to one dimension. We then take these 1D data as input to our second model - Multiple Layer Perception（MLP, supervised learning）. We apply MLP model to predict stocks’ future returns, thereby constructing the portfolio.
Finally, this paper evaluates the investment strategy through the empirical analysis. In conclusion, the strategy deliver an average annualized return of 22.69% and an average annualized Sharpe Ratio of 1.49, which all outperform than Taiwan Capitalization Weighted Stock Index（TAIEX）.
第一章 緒論 8
第一節 研究動機與研究背景 8
第二節 研究目的 9
第三節 研究流程 10
第二章 文獻探討 11
第一節 深度學習文獻探討 11
第二節 深度學習運用於股票之相關文獻探討 12
第三章 研究方法 14
第一節 資料庫建置 14
第二節 自動編碼器（AutoEncdoer) 16
第三節 多層感知機（Multiple Layer Perception） 20
第四節 交易策略建置與應用 25
第五節 績效指標說明 27
第四章 實證結果分析 28
第ㄧ節 實證分析樣本來源 28
第二節 固定持有期間績效分析 28
第三節 不固定持有期間績效分析 40
第五章 結論與未來研究方向建議 43
第ㄧ節 結論 43
第二節 未來研究方向建議 44
參考文獻 45
附 錄 47
[1] Chen, T. and Chen, F. (2016). An intelligent pattern recognition model for supporting investment decisions in stock market. Information Sciences, 346-347, 261-274.
[2] Ding, X., Zhang, Y., Liu T. and Duan J. (2015). Deep Learning for Event-Driven Stock Prediction. IJCAI'15 Proceedings of the 24th International Conference on Artificial Intelligece, 2327-2333.
[3] Fama, E. F. (1998). Market efficiency, long-term returns, and behavioral finance. Journal of financial economics, 49(3), 283-306.
[4] Fischer, T. and Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.
[5] He, K., Zhang, X., Ren, S. and Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[6] Hinton, G. E., Osindero, S. and Yee, W. (2006). A fast learning algorithm for deep belief nets. Neural computation, 18(7), 1527-1554.
[7] Hu, G., Hu, Y., Yang, K., Yu, Z., Sung, F., Zhang, Z., …Miemie, Q. (2018). Deep Stock Representation Learning: From Candlestick Charts to Investment Decisions. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[8] Hubel, D. H. and Wiesel, T. N. (1962). Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. Journal of Physiology, 160(1), 106-154.
[9] Krizhevsky, A., Sutskever, I. and Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems, 25(2), 1097-1105.
[10] Lecun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
[11] Masci, J., Meier U., Cireşan, D. and Schmidhuber, J. (2011). Stacked convolutional auto-encoders for hierarchical feature extraction. Artificial Neural Networks and Machine Learning - ICANN. 52-59.
[12] Ranjan R., Patel V. M. and Chellappa R. (2017). Hyperface: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. The IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(1), 121-135.
[13] Simonyan, K. and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556.
[14] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed S., Anguelov, D., Erhan, D., Vanhoucke, V. and Rabinovich, A. (2015). Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[15] Takeuchi, L. and Lee, Y. (2013). Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks. Stanford Technology Report.
