結合門控迴圈單元和知識圖譜嵌入的股票趨勢預測｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	洪子傑 Zih-Jie Hong
論文名稱：	結合門控迴圈單元和知識圖譜嵌入的股票趨勢預測 Stock Trend Prediction with Gated Recurrent Unit and Knowledge Graph Embedding
指導教授：	呂永和 Yung-Ho Leu
口試委員:	楊維寧 Wei-Ning Yang 陳雲岫 Yun-Shiow Chen
學位類別：	碩士 Master
系所名稱：	管理學院 - 資訊管理系 Department of Information Management
論文出版年：	2021
畢業學年度：	109
語文別：	英文
論文頁數：	36
中文關鍵詞：	股價趨勢預測、迴圈神經網路、知識圖譜、門控迴圈單元
外文關鍵詞：	Stock Price Trend Prediction, Recurrent Neural Network, Knowledge Graph, Gated Recurrent Unit
相關次數：	點閱：241 下載：5
分享至:	分享至facebook 分享至twitter

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

上一筆

多年來，投資者一直對股價走勢感興趣，以做出明智的投資決策。最近，許多研究者提出使用機器學習方法來預測股票價格的趨勢。在所有的機器學習演算法中，遞迴神經網路（RNN）被證明是非常有效的序列預測演算法，包括股票價格的趨勢預測。
傳統的股票價格趨勢預測方法只使用股票的歷史價格。然而，研究表明，文字資訊，特別是與股票相關的新聞資訊，提供了許多有用的資訊。因此，在本論文中，我們建議使用知識圖對財經新聞標題中的事件進行編碼，以幫助預測股票價格趨勢。該方法利用歷史股價和技術指標等傳統特徵，利用新聞標題中的事件來預測股價的趨勢。
實驗結果表明，與其他機器學習方法相比，該方法具有更高的學習精度。此外，對特徵的重要性分析表明，事件嵌入所提供的特徵對於股票價格趨勢預測是必不可少的。

For many years, investors were interested in the stock price trend to make a wise investment decision. Recently, many researchers proposed to use machine learning methods for the trend prediction of a stock price. Among all the machine learning algorithms, the Recurrent Neural Networks (RNNs) have been proven to be very effective for sequence prediction, including the trend prediction of a stock price.
Traditional methods for trend prediction of the stock price used only the historical prices of the stock. However, it is shown that textual information, especially the news information related to a stock, provided much useful information. Therefore, in this thesis, we proposed using the knowledge graph to encode the events from financial news headlines to help predict stock price trends. The proposed method used the traditional features such as the historical stock prices and the technical indicators and used the events from the news headlines to predict the trend of a stock price.
The experimental results showed that the proposed method achieved higher accuracy than the other machine learning methods. Furthermore, the importance analysis of the features showed that the features provided by the event embedding are essential for stock price trend prediction.

ABSTRACT    i
ACKNOWLEDGEMENT    ii
TABLE OF CONTENTS    iii
LIST OF FIGURES    v
LIST OF TABLES    vi
Chapter 1. Introduction    1
1. Background    1
2. Motivation    1
3. Purpose    2
Chapter 2. Related Work    3
1. Deep Model for Stock Trend Prediction    3
2. Knowledge Graph Embedding    4
3. Recurrent Neural Network    6
3.1.    Long Short-Term Memory    7
3.2.    Gated Recurrent Unit    10
Chapter 3. Proposed Approach    12
1. Overview    12
2. Date Description    13
3. Data Preprocessing    15
3.1.    Sliding Window    15
3.2.    Normalization    16
3.3.    Split Dataset    16
4. Event Embedding    16
4.1.    Event Extraction and Structuralization    17
4.2.    TransE    17
5. Model Establishment    19
5.1.    Gated Recurrent Unit Network    20
6. Evaluation Metric    21
6.1.    F1-Score    21
6.2.    Profit Performance    22
Chapter 4. Experimental Result    23
1. Experimental Environment    23
2. Dataset Description    23
3. Experimental Variables    24
3.1.    Gated Recurrent Unit Parameters    24
4. Evaluation of Prediction Models    26
5. Event Embedding Importance    27
6. Discussion    29
Chapter 5. Conclusions and Future Research    30
1. Conclusions    30
2. Future Research    30
REFERENCES    32

                                

[1] D. Galai and R. W. Masulis. (1976). The option pricing model and the risk factor of stock. Journal of Financial Economics, vol. 3, no.1-2, 53-81.

[2] Nguyen, T.H., Shirai, K., Velcin, J. (2015). Sentiment analysis on social media for stock movement prediction. Expert Syst. Appl, 42, 9603-9611.

[3] Qiao, L., Yang, L., Hong, D., Yao, L., Zhiguang, (2014). Knowledge graph construction techniques. J. Comput. Res. Dev, 53(3), 649–652

[4] H. Paulheim and P. Cimiano. (2016). Knowledge graph refinement: A survey of approaches and evaluation methods. Journal of Web Semantics: Science, Services and Agents on the World Wide Web, vol. 8, no. 3, 489-508.

[5] Eugene F Fama. (1965). The behavior of stock-market prices. The journal of Business, 38(1), 34-105.

[6] Wang, B., Huang, H., Wang, X. (2012). A Novel Text Mining Approach to Financial Time Series Forecasting. Neurocomputing, 83(6), 13645.

[7] Markowitz, H. (1952). Portfolio selection[J]. The Journal of Finance, 7(1), 77-91.

[8] A. Khadjeh Nassirtoussi, S. Aghabozorgi, T. Ying Wah, and D. C. L. Ngo. (2014). Text mining for market prediction: a systematic review. Expert Systems with Applications, vol. 41, no. 16, 7653-7670.

[9] P. C. Tetlock. (2007). Giving content to investor sentiment: The role of media in the stock market. Journal of Finance, vol. 62, no. 3, 1139-1168.

[10] K. Chen, P. Luo, L. Liu, and W. Zhang. (2018). "News, search and stock co-movement: Investigating information diffusion in the financial market. Electronic Commerce Research and Applications, vol. 28, 159-171.

[11] Harris, G. (2016). A Survey of Deep Learning Techniques Applied to Trading.

[12] Ding, X., Zhang, Y., Liu, T., Duan, J. (2015). Deep learning for event-driven stock prediction, IJCAI International Joint Conference on Artificial Intelligence, 2327-2333.

[13] Heaton, J.B., Polson, N.G., Witte, J.H. (2016). Deep Learning in Finance, 1-20.

[14] Freddy LeCue Chen, Jiaoyan and, Jeff Z. Pan, and Huajun Chen. (2017). Learning from Ontology Streams with Semantic Concept Drift. In IJCAI, 957-963.

[15] Bordes, A., Usunier, N., Weston, J., Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. Adv. NIPS, 26, 2787-2795.

[16] Wang, Z., Zhang, J., Feng, J., Chen, Z. (2014). Knowledge graph embedding by translating on hyperplanes. AAAI Conf. Artif. Intell, 14, 1112-1119.

[17] Lin, H., Liu, Y., Wang, W., Yue, Y., Lin, Z. (2017). Learning entity and relation embeddings for knowledge resolution. Procedia Comput. Sci, 108, 345-354.

[18] Ji, G., He, S., Xu, L., Liu, K., Zhao, J. (2015). Knowledge graph embedding via dynamic mapping matrix. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, vol, 1, 687-695.

[19] D. E. Rumelhart, G. E. Hinton, R. J. Williams. (1986). Learning internal representations by error propagation. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1, 318-362.

[20] L.K. Hansen, P. Salamon. (1990). Neural Network Ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(10), 993-1001.

[21] Sepp Hochreiter, Jurgen Schmidhuber. (1997). . Neural Computation, 9(8), 1735-1780.

[22] Hasim Sak, Andrew Senior, Francoise Beaufays. (2014). Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. ArXiv 2014, 1-3.

[23] K. Cho, B. van Merrienboer, D. Bahdanau, Y. Bengio (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv, 1409.1259

[24] Chan, W.C (2003). Stock price reaction to news and no-news: Drift and reversal after headlines. J. Financ. Econ, 70, 223-260.

[25] Fehrer, R., Feuerriegel, S. (2015). : Improving decision analytics with deep learning: The case of financial disclosures, 1-39.

[26] Lin, X., Yang, Z., Song, Y. (2011). Expert systems with applications intelligent stock trading system based on improved technical analysis and echo state network. Expert Syst. Appl, 38, 11347-11354.

[27] Wilder, J. (1978). New concepts in technical trading systems. Greensboro, N.C.: Trend Research.

[28] Oren Etzioni, Michael Cafarella, and Michele Banko. (2014). OPEN INFORMATION EXTRACTION.

[29] LeCun, Y., Bengio, Y., Hinton, G. (2015). Deep learning. Nature 521, 436-444

[30] Kraus, M., Feuerriegel, S. (2017). Decision support from financial disclosures with deep neural networks and transfer learning. Decis. Support Syst. 104, 38-48

[31] Song, Yuan. (2018). Stock Trend Prediction: Based on Machine Learning Methods

[32] Laurens van der Maaten., Geoffrey Hinton. (2008). Visualizing Data using t-SNE. Journal of Machine Learning Research, 9, 2579-2605

簡易檢索 / 詳目顯示

相關論文