基於財經金融新聞的每日股票趨勢預測｜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：	林峻宇 JUN-YU LIN
論文名稱：	基於財經金融新聞的每日股票趨勢預測 Study on Financial News based Daily Stock Trend Prediction
指導教授：	蘇順豐 Shun-Feng Su 陳建中 Jiann-Jone Chen
口試委員:	陸敬互 Ching-Hu Lu 王文俊 Wen-June Wang 姚立德 Leehter Yao
學位類別：	碩士 Master
系所名稱：	電資學院 - 電機工程系 Department of Electrical Engineering
論文出版年：	2021
畢業學年度：	109
語文別：	英文
論文頁數：	60
中文關鍵詞：	深度學習、遞歸循環神經網路、卷積神經網路、長短期記憶神經網路、每日股票趨勢預測
外文關鍵詞：	Deep learning, Recurrent neural network, Convolution neural network, Long Short-Term Memory neural network, Daily stock trend forecasting
相關次數：	點閱：508 下載：0
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

預測股票趨勢一直是金融投資者以及相關研究人員所關注的議題，然而多元的影響因素，如：政治、經濟、媒體觀點、社群討論等，使得評估過程產生許多阻力。本項研究是藉網路爬蟲蒐羅的金融新聞所建立的語料庫，來訓練我們的詞向量模型。這種方式可以透過新聞的串聯來改善文章的主觀意識，並利用深度學習的方法來預測台灣積體電路製造公司（TSMC）的每日股價趨勢。我們將金融新聞文章和技術指標導入到設計的模型後，利用了卷積神經網路在特徵提取方面的優勢結合長短期記憶神經網路在長時間預測上的優良表現，於是，提出了遞歸循環神經網路的架構來推演未來股價趨勢。這樣的架構可以更精確地捕捉金融文本的關鍵特徵和時間特徵，在對台積電每日股票趨勢的預測結果上，數據顯示：比起現有其他的預測框架，準確率可以提高20個百分點；比起傳統的卷積神經網路，準確率也提高了五個百分點；而比起單用新聞標題預測，混合輸入（新聞文章與技術指標結合）可提高八個百分點。

This study is to consider financial news obtained from web crawlers and use them to train our own corpus and word vector models. Our approach can improve the subjective awareness of news articles by cascading news and utilizes a deep learning approach to predict the daily stock price trend of Taiwan Semiconductor Manufacturing Company (TSMC). Predicting stock trends has long been a topic of interest to scholars and investors. However, a large number of external factors such as politics, economy, news, social media, etc., create a lot of uncertainty in the evaluation process. In our designed model, the financial news headlines and a set of technical indicators are used as the inputs to the model proposed. In our implementation, a Recurrent Convolutional Neural Network is employed to predict the stock price trend by exploiting the advantages of Convolutional Neural Networks for feature extraction and the properties of Long Short-Term Memory Neural Networks for time series prediction. From our experiments, the proposed architecture can better capture the local features of news text and its temporal features. Compared with an existing prediction framework, the proposed system can get 20 percentages more in the prediction accuracy. In our analysis, it is shown that the proposed network can improve the prediction result by 5 percentages over a traditional Convolutional Neural Network for daily stock trends prediction of TSMC and that the use of hybrid inputs (news titles combined with technical indicators) outperforms the use of news titles only by 8 percentages.

中文摘要    I
Abstract    II
致謝    III
Table of Contents    IV
List of Figures    VII
List of Tables    VIII
Chapter 1    Introduction    1
1    Background and Motivation    1
2    Stock Market Prediction    2
3    Contributions    4
4    Thesis Organization    5
Chapter 2    Related Work    6
1    Stock Prediction Depending on Technical Analysis    6
2    Stock Prediction Depending on Fundamental Analysis    7
2.1    Emotion Analysis    7
2.2    Text Information Analysis    8
2.3    Event Analysis    8
3    Stock Prediction Depending on Hybrid Analysis    9
Chapter 3    Methodology    13
1    Input Data    13
2    Data Preprocessing    14
2.1    Jieba    15
2.2    Word2vec    16
2.3    Zero-padding    19
2.4    Cascade News    20
2.5    Technical Indicators Pre-process    21
3    Convolutional Neural Network    22
3.1    Text-CNN Network Architecture    22
3.2    Hyperparameter Tuning for Text-CNN    24
4    Long Short-Term Memory Networks    26
4.1    Recurrent Neural Network Architecture    26
4.2    Long Short-Term Memory Network Architecture    27
5    Propose Model Design    30
5.1    Word Embedding Layer    30
5.2    Technical Indicators Embedding Layer    31
5.3    Output Layer    31
Chapter 4    Experiments    32
1    Dataset    32
2    Evaluation Metric    33
2.1    Predictive Accuracy    33
2.2    Losses    35
3    Experiments    35
3.1    Abbreviation of Model    36
3.2    Training Detail    37
4    Implementation Details    38
4.1    Tuned Hyperparameters    38
4.2    Environment    40
5    Results    41

                                

[1] B. G. Malkiel, "A Random Walk Down Wall Street," W. W. Norton, New York, 1999.
[2] Z. Zou and Z. Qu, "Using LSTM in stock prediction and quantitative trading," CS230: Deep Learning, Winter, 2020.
[3] M. Roondiwala, H. Patel, and S. Varma, "Predicting stock prices using LSTM," International Journal of Science and Research (IJSR), vol. 6, no. 4, pp. 1754-1756, 2017.
[4] S. Mehtab and J. Sen, "Stock price prediction using CNN and LSTM-based deep learning models," International Conference on Decision Aid Sciences and Application (DASA), pp. 447-453, 2020.
[5] K. Chen, Y. Zhou, and F. Dai, "A LSTM-based method for stock returns prediction: A case study of China stock market," IEEE International Conference on Big Data (Big Data), pp. 2823-2824, 2015.
[6] V. S. Pagolu, K. N. Reddy, G. Panda, and B. Majhi, "Sentiment analysis of twitter data for predicting stock market movements," International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), pp. 1345-1350, 2016.
[7] J. Kim, J. Seo, M. Lee, and J. Seok, "Stock price prediction through the sentimental analysis of news articles," Eleventh International Conference on Ubiquitous and Future Networks (ICUFN), pp. 700-702, 2019.
[8] 賀安平, "從新聞文章預測股票走勢: 使用 SVM 與 LDA 演算法," 碩士, 資訊管理研究所碩士班, 國立高雄應用科技大學, 2016.
[9] 陳敘融, "利用財經新聞預測台灣股市大盤的漲跌," 碩士, 資訊工程學系研究所, 國立嘉義大學, 嘉義市, 2017.
[10] X. Zhang and Y. LeCun, "Text understanding from scratch," arXiv preprint arXiv:1502.01710, 2015.
[11] Y. Kim, "Convolutional neural networks for sentence classification," arXiv preprint arXiv:1408.5882, 2014.
[12] N. Kalchbrenner, E. Grefenstette, and P. Blunsom, "A convolutional neural network for modelling sentences," arXiv preprint arXiv:1404.2188, 2014.
[13] R. Collobert and J. Weston, "A unified architecture for natural language processing: Deep neural networks with multitask learning," Proceedings of the 25th international conference on Machine learning, pp. 160-167, 2008.
[14] T. Mikolov, M. Karafiát, L. Burget, J. Černocký, and S. Khudanpur, "Recurrent neural network based language model," Eleventh annual conference of the international speech communication association, 2010.
[15] O. Irsoy and C. Cardie, "Opinion mining with deep recurrent neural networks," Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 720-728, 2014.
[16] J. Xu, D. Chen, X. Qiu, and X. Huang, "Cached long short-term memory neural networks for document-level sentiment classification," arXiv preprint arXiv:1610.04989, 2016.
[17] X. Wang, Y. Liu, C.-J. Sun, B. Wang, and X. Wang, "Predicting polarities of tweets by composing word embeddings with long short-term memory," Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1343-1353, 2015.
[18] C. Zhou, C. Sun, Z. Liu, and F. Lau, "A C-LSTM neural network for text classification," arXiv preprint arXiv:1511.08630, 2015.
[19] S. Lai, L. Xu, K. Liu, and J. Zhao, "Recurrent convolutional neural networks for text classification," Twenty-ninth AAAI conference on artificial intelligence, 2015.
[20] Y. Xu, W. Lin, and Y. Hu, "Stock trend prediction using historical data and financial online news," IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), pp. 1507-1512, 2020.
[21] H. Ni, S. Wang, and P. Cheng, "A hybrid approach for stock trend prediction based on tweets embedding and historical prices," World Wide Web, vol. 24, no. 3, pp. 849-868, 2021.
[22] C.-H. Chen and P. Shih, "A stock trend prediction approach based on Chinese news and technical indicator using genetic algorithms," IEEE Congress on Evolutionary Computation (CEC), pp. 1468-1472, 2019.
[23] M. R. Vargas, B. S. L. P. d. Lima, and A. G. Evsukoff, "Deep learning for stock market prediction from financial news articles," IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), pp. 60-65, 2017.
[24] T. Sun, J. Wang, P. Zhang, Y. Cao, B. Liu, and D. Wang, "Predicting stock price returns using microblog sentiment for Chinese stock market," 2017 3rd International Conference on Big Data Computing and Communications (BIGCOM), pp. 87-96, 2017.
[25] S. Mohan, S. Mullapudi, S. Sammeta, P. Vijayvergia, and D. C. Anastasiu, "Stock price prediction using news sentiment analysis," IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService), pp. 205-208, 2019.
[26] X. Ding, Y. Zhang, T. Liu, and J. Duan, "Deep learning for event-driven stock prediction," Twenty-fourth international joint conference on artificial intelligence, 2015.
[27] X. Ding, Y. Zhang, T. Liu, and J. Duan, "Using structured events to predict stock price movement: An empirical investigation," Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1415-1425, 2014.
[28] 李哲宇, "以遞歸卷積神經網路擷取財經新聞知識預測股價," 碩士, 資訊系統與應用研究所, 國立清華大學, 2017.
[29] R. Akita, A. Yoshihara, T. Matsubara, and K. Uehara, "Deep learning for stock prediction using numerical and textual information," IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), pp. 1-6, 2016.
[30] Q. Le and T. Mikolov, "Distributed representations of sentences and documents," International conference on machine learning, pp. 1188-1196, 2014.
[31] 邱彥誠, "應用人工智慧於股市新聞與情感分析預測股價走勢," 碩士, 資訊管理研究所, 國立臺北大學, 新北市, 2020.
[32] T. Mikolov, K. Chen, G. Corrado, and J. Dean, "Efficient estimation of word representations in vector space," arXiv preprint arXiv:1301.3781, 2013.
[33] Y. Zhai, A. Hsu, and S. K. Halgamuge, "Combining news and technical indicators in daily stock price trends prediction," International symposium on neural networks, pp. 1087-1096, 2007.
[34] Y. Zhang and B. Wallace, "A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification," arXiv preprint arXiv:1510.03820, 2015.
[35] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, pp. 318–362, 1986.
[36] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[37] H. Palangi et al., "Deep sentence embedding using long short-term memory networks: Analysis and application to information retrieval," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 4, pp. 694-707, 2016.
[38] Z. Hu, W. Liu, J. Bian, X. Liu, and T.-Y. Liu, "Listening to chaotic whispers: A deep learning framework for news-oriented stock trend prediction," Proceedings of the eleventh ACM international conference on web search and data mining, pp. 261-269, 2018.
[39] M. R. Vargas, C. E. dos Anjos, G. L. Bichara, and A. G. Evsukoff, "Deep leaming for stock market prediction using technical indicators and financial news articles," International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2018.

全文公開日期 2026/09/06 (校內網路)
全文公開日期 2026/09/06 (校外網路)
全文公開日期 2026/09/06 (國家圖書館：臺灣博碩士論文系統)

簡易檢索 / 詳目顯示

相關論文