學術產出-Theses
Article View/Open
Publication Export
-
題名 深度學習應用於股價走勢之研究：以大陸市場為例
An Empirical Study of Deep Learning to the Trend of Stock Price in China Market作者 張力元
Chang, Li-Yuan貢獻者 黃泓智
Huang, Hong-Chih
張力元
Chang, Li-Yuan關鍵詞 大陸股市
深度學習
股價走勢
技術指標
China stock market
Deep learning
Stock price trend
Technical indicators日期 2018 上傳時間 29-Aug-2018 15:49:15 (UTC+8) 摘要 股價的未來走勢一直是一個未知且令人充滿興趣的研究領域，過去已有許多學者提出各種理論以論述其觀點，如今我們身處於人工智慧的時代，各種機器學習的應用已顛覆我們對生活方式的認知。本文建構一套神經網路的簡單序列模型，以幾種常見的技術指標為主要特徵，並選定未來二十日的股價漲跌作為預測目標，同時考慮交易成本，使用定錨式移動視窗的方式，將兩者之間的關係透過神經網路進行深度學習，藉以預測未來一年股價走勢的分類情況，從而挑選出具有上漲潛力的股票，以其分類結果作為判斷買賣時機的依據，將模型預測上漲機率較高的前幾檔股票納入投資組合，以實現自動化的資產配置，同時也考慮不同情境下的配置方式。實證結果顯示本文的主要策略相比大盤績效，其年化報酬率在大多數的年度皆有不錯表現，在七年回測期間的年化報酬率達13.67%，惟其標準差也稍高。
The future trend of stock prices has always been an unknown and interesting research field. Many scholars have proposed various theories to discuss their views. Now we are in the era of artificial intelligence, and the various application of machine learning has subverted our perception of lifestyle. This paper constructs a simple sequential model of neural network, with several common technical indicators as the main features, and selects the rise or fall of the stock prices in the next twenty days as the predicting target, while considering the transaction cost and using the anchored moving window method. The relationship between this two is deep learning through the neural network to predict the classification of stock price movements in the coming year, so as to select stocks with rising potential, and use the classification results as a basis for judging the timing of trading. The model predicting the first few stocks with higher probability are included in the portfolio to achieve automated asset allocation, while considering the configuration in different scenarios. The empirical results show that the main strategy of this paper has a good performance in most years compared to the market performance. The annualized rate of return during the seven-year back-testing period is 13.67%, but the standard deviation is also slightly higher.參考文獻 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. Chong, T. & Ng, W. (2008). Technical analysis and the London stock exchange: testing the MACD and RSI rules using the FT30. Applied Economics Letters, 15(14), 1111-1114. Dean, J. (2016). Building machine learning systems that understand. In Proceedings of the 2016 International Conference on Management of Data (pp. 1-1). ACM. Huval, B., Wang, T., Tandon, S., Kiske, J., Song, W., Pazhayampallil, J., & Mujica, F. (2015). An Empirical Evaluation of Deep Learning on Highway Driving. arXiv preprint arXiv:1504.01716. Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint arXiv:1502.03167. Khan, A. & Gour, B. Neural Networks with Technical Indicators Identify Best Timing to Invest in the Selected Stocks. Kingma, D. & Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980. Mizuno, H., Kosaka, M., Yajima, H., & Komoda, N. (1998). Application of Neural Network to Technical Analysis of Stock Market Prediction. Studies in Informatic and control, 7(3), 111-120. Nelson, D., Pereira, A., & Oliveira, R. (2017). Stock Market`s Price Movement Prediction with LSTM Neural Networks. In Neural Networks (IJCNN), 2017 International Joint Conference on (pp. 1419-1426). IEEE. Poulos, J. (2015). Predicting Stock Market Movement with Deep RNNs. Sezer, O., Ozbayoglu, A., & Dogdu, E. (2017). An Artificial Neural Network-based Stock Trading System Using Technical Analysis and Big Data Framework. In Proceedings of the SouthEast Conference (pp. 223-226). ACM. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. The Journal of Machine Learning Research, 15(1), 1929-1958. Sun, Y., Wang, X., & Tang, X. (2014). Deep Learning Face Representation from Predicting 10,000 Classes. In Proceedings of the IEEE conference on computer vision and pattern recognition(pp. 1891-1898). Wang, D., Khosla, A., Gargeya, R., Irshad, H., & Beck, A. (2016). Deep Learning for Identifying Metastatic Breast Cancer. arXiv preprint arXiv:1606.05718. Xiong, R., Nichols, E., & Shen, Y. (2015). Deep Learning Stock Volatility with Google Domestic Trends. arXiv preprint arXiv:1512.04916. 描述 碩士
國立政治大學
風險管理與保險學系
105358012資料來源 http://thesis.lib.nccu.edu.tw/record/#G0105358012 資料類型 thesis dc.contributor.advisor 黃泓智 zh_TW dc.contributor.advisor Huang, Hong-Chih en_US dc.contributor.author (Authors) 張力元 zh_TW dc.contributor.author (Authors) Chang, Li-Yuan en_US dc.creator (作者) 張力元 zh_TW dc.creator (作者) Chang, Li-Yuan en_US dc.date (日期) 2018 en_US dc.date.accessioned 29-Aug-2018 15:49:15 (UTC+8) - dc.date.available 29-Aug-2018 15:49:15 (UTC+8) - dc.date.issued (上傳時間) 29-Aug-2018 15:49:15 (UTC+8) - dc.identifier (Other Identifiers) G0105358012 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/119725 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 風險管理與保險學系 zh_TW dc.description (描述) 105358012 zh_TW dc.description.abstract (摘要) 股價的未來走勢一直是一個未知且令人充滿興趣的研究領域，過去已有許多學者提出各種理論以論述其觀點，如今我們身處於人工智慧的時代，各種機器學習的應用已顛覆我們對生活方式的認知。本文建構一套神經網路的簡單序列模型，以幾種常見的技術指標為主要特徵，並選定未來二十日的股價漲跌作為預測目標，同時考慮交易成本，使用定錨式移動視窗的方式，將兩者之間的關係透過神經網路進行深度學習，藉以預測未來一年股價走勢的分類情況，從而挑選出具有上漲潛力的股票，以其分類結果作為判斷買賣時機的依據，將模型預測上漲機率較高的前幾檔股票納入投資組合，以實現自動化的資產配置，同時也考慮不同情境下的配置方式。實證結果顯示本文的主要策略相比大盤績效，其年化報酬率在大多數的年度皆有不錯表現，在七年回測期間的年化報酬率達13.67%，惟其標準差也稍高。 zh_TW dc.description.abstract (摘要) The future trend of stock prices has always been an unknown and interesting research field. Many scholars have proposed various theories to discuss their views. Now we are in the era of artificial intelligence, and the various application of machine learning has subverted our perception of lifestyle. This paper constructs a simple sequential model of neural network, with several common technical indicators as the main features, and selects the rise or fall of the stock prices in the next twenty days as the predicting target, while considering the transaction cost and using the anchored moving window method. The relationship between this two is deep learning through the neural network to predict the classification of stock price movements in the coming year, so as to select stocks with rising potential, and use the classification results as a basis for judging the timing of trading. The model predicting the first few stocks with higher probability are included in the portfolio to achieve automated asset allocation, while considering the configuration in different scenarios. The empirical results show that the main strategy of this paper has a good performance in most years compared to the market performance. The annualized rate of return during the seven-year back-testing period is 13.67%, but the standard deviation is also slightly higher. en_US dc.description.tableofcontents 第一章、緒論 1 第一節、研究動機與背景 1 第二節、研究目的 4 第三節、研究流程 5 第二章、文獻回顧 6 第三章、研究方法 11 第一節、前言 11 第二節、深度學習概述 12 第三節、模型變數 19 第四節、投資策略 23 第五節、績效指標 25 第四章、實證結果分析 27 第一節、實證分析樣本來源 27 第三節、情境分析 35 第五章、結論與建議 45 第一節、結論 45 第二節、未來研究方向建議 46 參考文獻 47 附錄 49 zh_TW dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0105358012 en_US dc.subject (關鍵詞) 大陸股市 zh_TW dc.subject (關鍵詞) 深度學習 zh_TW dc.subject (關鍵詞) 股價走勢 zh_TW dc.subject (關鍵詞) 技術指標 zh_TW dc.subject (關鍵詞) China stock market en_US dc.subject (關鍵詞) Deep learning en_US dc.subject (關鍵詞) Stock price trend en_US dc.subject (關鍵詞) Technical indicators en_US dc.title (題名) 深度學習應用於股價走勢之研究：以大陸市場為例 zh_TW dc.title (題名) An Empirical Study of Deep Learning to the Trend of Stock Price in China Market en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 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. Chong, T. & Ng, W. (2008). Technical analysis and the London stock exchange: testing the MACD and RSI rules using the FT30. Applied Economics Letters, 15(14), 1111-1114. Dean, J. (2016). Building machine learning systems that understand. In Proceedings of the 2016 International Conference on Management of Data (pp. 1-1). ACM. Huval, B., Wang, T., Tandon, S., Kiske, J., Song, W., Pazhayampallil, J., & Mujica, F. (2015). An Empirical Evaluation of Deep Learning on Highway Driving. arXiv preprint arXiv:1504.01716. Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint arXiv:1502.03167. Khan, A. & Gour, B. Neural Networks with Technical Indicators Identify Best Timing to Invest in the Selected Stocks. Kingma, D. & Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980. Mizuno, H., Kosaka, M., Yajima, H., & Komoda, N. (1998). Application of Neural Network to Technical Analysis of Stock Market Prediction. Studies in Informatic and control, 7(3), 111-120. Nelson, D., Pereira, A., & Oliveira, R. (2017). Stock Market`s Price Movement Prediction with LSTM Neural Networks. In Neural Networks (IJCNN), 2017 International Joint Conference on (pp. 1419-1426). IEEE. Poulos, J. (2015). Predicting Stock Market Movement with Deep RNNs. Sezer, O., Ozbayoglu, A., & Dogdu, E. (2017). An Artificial Neural Network-based Stock Trading System Using Technical Analysis and Big Data Framework. In Proceedings of the SouthEast Conference (pp. 223-226). ACM. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. The Journal of Machine Learning Research, 15(1), 1929-1958. Sun, Y., Wang, X., & Tang, X. (2014). Deep Learning Face Representation from Predicting 10,000 Classes. In Proceedings of the IEEE conference on computer vision and pattern recognition(pp. 1891-1898). Wang, D., Khosla, A., Gargeya, R., Irshad, H., & Beck, A. (2016). Deep Learning for Identifying Metastatic Breast Cancer. arXiv preprint arXiv:1606.05718. Xiong, R., Nichols, E., & Shen, Y. (2015). Deep Learning Stock Volatility with Google Domestic Trends. arXiv preprint arXiv:1512.04916. zh_TW dc.identifier.doi (DOI) 10.6814/THE.NCCU.RMI.009.2018.F08 -
