跳到主要內容

臺灣博碩士論文加值系統

(35.172.136.29) 您好!臺灣時間:2021/07/26 20:43
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:陳秀蓁
研究生(外文):Chen, Xiu-Zhen
論文名稱:不同層面指標之股市漲跌幅探勘預測
論文名稱(外文):Using Different Indicators to Predict the Increase or Fall in Stock Price with Mining Technology
指導教授:黃河銓黃河銓引用關係
指導教授(外文):HUANG, HO-CHUAN
口試委員:楊棠堯陳聰毅
口試委員(外文):YANG, TARNG-YAOCHEN, TSONG-YI
口試日期:2020-07-27
學位類別:碩士
校院名稱:國立高雄科技大學
系所名稱:智慧商務系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:74
中文關鍵詞:股市預測機器學習資料探勘網頁爬蟲
外文關鍵詞:Stock ForecastMachine LearningData MiningWeb Crawler
相關次數:
  • 被引用被引用:1
  • 點閱點閱:56
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本研究目的為探討不同股市分析層面變數是否能夠使股市預測能力提高,並探討及比較不同演算法對股市走向的預測能力,最後探討及建置股市預測模型,使投資人能更容易且正確的預測股市走向。
因此本研究使用爬蟲技術蒐集鉅亨網中的半導體類股,2018年1月1日至2019年12月31日資料並進行資料處理,接著進行變數的計算處理,擷取股市資訊中的歷史價格,計算出基本分析指標,並使用TA-Lib計算出158個技術指標三種層面指標,接著進行相關係數分析篩選欄位作為模型輸入變數,建立五種演算法模型,分別為支援向量機、人工神經網路、卷積神經網路、循環神經網路、隨機森林,最後使用準確度、精確度、F1值、召回率等評估方式評估模型,以此來探討不同演算法模型及不同股市分析層面指標之預測能力。
研究結果發現,使用歷史價格、基本分析指標、技術分析指標作為模型輸入變數時,加入技術分析指標過後模型準確率有明顯提高。比較五種模型演算法時可以發現人工神經網路模型以及卷積神經網路模型在最初只使用歷史價格作為輸入變數時,比起其它模型演算法有較高之準確率,但當加入基本分析指標以及技術分析指標後,幾乎所有的模型演算法都提升至65%準確率上下,因此可以證明技術指標作為輸入變數能夠提升模型預測能力,此外,當模型輸入變數僅有歷史價格時,人工神經網路以及卷積神經網路之模型準確率相較其它模型高出10至20%。

The purpose of this study is to investigate whether different indicators and algorithms could improve stock market predictions or not. Therefore, this study constructed a stock market prediction model so that investors can predict stock prices easily.
Web crawler technology has been used to collect the semiconductor stocks data from the Anue website and the period of collected data runs from January 1, 2018 to December 31, 2019. Collecting data is the first step in data processing and then analyze 158 analytical variables and correlation coefficient. After that, different algorithms, such as the support vector machine (SVM), artificial neural network (ANN), convolutional neural network (CNN), recurrent neural network (RNN), and random forest (RF), were constructed to predict stock price for fundamental analysis. Finally, the measurements, such as accuracy, precision, recall, and F1 value, were also used to evaluate the prediction performance of the proposed models.
The results found that when using all analytical variables as the input parameters in the model, especially for the technical analysis indicators, the prediction accuracy of the model was significantly improved. When the historical prices were used as the input parameters, the predication accuracy of both the ANN and CNN models is higher than that of other models. After adding both basic analysis and technical analysis indicators, almost all models' accuracy had been improved to around 65%. Therefore, this result demonstrated that technical analysis indicators could improve the predictability of stock price models. Finally, when historical prices were used as input parameters, the prediction accuracy of ANN and CNN models was approximately 10-20% higher than that of other models.

摘要 ii
ABSTRACT iii
誌謝 iv
目錄 v
表目錄 ix
圖目錄 xi
一、緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 論文架構 2
二、文獻探討 4
2.1 股市分析層面 5
2.1.1 基本分析 5
2.1.2 技術分析 5
2.2 資料探勘 6
2.3 支援向量機 9
2.4 深度學習 11
2.5人工神經網絡 12
2.6 卷積神經網路 13
2.7 循環神經網路 14
2.8 集成模型 16
2.9 隨機森林 16
2.10 文獻比較 17
三、研究方法 19
3.1 研究設計 19
3.1.1 資料蒐集 19
3.1.2 變數計算整理 23
3.1.3 資料處理 23
3.1.4 建立演算法模型 25
四、研究結果與討論 30
4.1 支援向量機模型結果 30
4.1.1 支援向量機歷史價格 30
4.1.2 支援向量機(加入基本分析指標) 31
4.1.3 支援向量機(加入技術分析指標) 33
4.1.4 支援向量機綜合討論 34
4.2 人工神經網路模型結果 35
4.2.1 人工神經網路歷史價格 35
4.2.2 人工神經網路(加入基本分析指標) 36
4.2.3 人工神經網路(加入技術分析指標) 38
4.2.4 人工神經網路綜合討論 39
4.3 卷積神經網路模型結果 40
4.3.1 卷積神經網路歷史價格 40
4.3.2 卷積神經網路(加入基本分析指標) 41
4.3.3 卷積神經網路(加入技術分析指標) 43
4.3.4 卷積神經網路綜合討論 44
4.4 循環神經網路模型結果 45
4.4.1 循環神經網路歷史價格 45
4.4.2 循環神經網路(加入基本分析指標) 46
4.4.3 循環神經網路(加入技術分析指標) 48
4.4.4 循環神經網路綜合討論 49
4.5 隨機森林模型結果 50
4.5.1 隨機森林歷史價格 50
4.5.2 隨機森林(加入基本分析指標) 51
4.5.3 隨機森林(加入技術分析指標) 53
4.5.4 隨機森林綜合討論 54
4.6 綜合討論 55
五、結論與未來研究 57
5.1 結論 57
5.2 未來研究方向與建議 58
參考文獻 59


王百祿(2007)。ARIMA 與適應性 SVM 之混合模型於股市指數預測之研究。國立成功大學資訊管理研究所學位論文,台南市。 取自https://hdl.handle.net/11296/x3yd3b
李尚益(2019)。一個使用長短期記憶神經網路模型於高頻交易環境的研究。國立高雄大學資訊工程學系碩士班碩士論文,高雄市。 取自https://hdl.handle.net/11296/7u72j4
陳昌捷(2015)。以倒傳遞類神經網路預測股市指數。國立宜蘭大學多媒體網路通訊數位學習碩士在職專班碩士論文,宜蘭縣。 取自https://hdl.handle.net/11296/2u52b6
賴嘉蔚(2018)。卷積神經網路預測時間序列能力分析。國立政治大學金融學系碩士論文,台北市。 取自https://hdl.handle.net/11296/y25ux2
Arévalo, A., Niño, J., Hernández, G., & Sandoval, J. (2016). High-frequency trading strategy based on deep neural networks. Paper presented at the International conference on intelligent computing.
Bengio, Y. (2009). Learning deep architectures for AI: Now Publishers Inc.
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
Bustos, O., & Pomares-Quimbaya, A. (2020). Stock Market Movement Forecast: A Systematic Review. Expert Systems with Applications, 113464.
Bustos, O., Pomares, A., & Gonzalez, E. (2017). A comparison between SVM and multilayer perceptron in predicting an emerging financial market: Colombian stock market. Paper presented at the 2017 Congreso Internacional de Innovacion y Tendencias en Ingenieria (CONIITI).
Cavalcante, R. C., Brasileiro, R. C., Souza, V. L., Nobrega, J. P., & Oliveira, A. L. (2016). Computational intelligence and financial markets: A survey and future directions. Expert Systems with Applications, 55, 194-211.
Chong, E., Han, C., & Park, F. C. (2017). Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications, 83, 187-205.
Di Persio, L., & Honchar, O. (2016). Artificial neural networks architectures for stock price prediction: Comparisons and applications. International journal of circuits, systems and signal processing, 10(2016), 403-413.
Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). The KDD process for extracting useful knowledge from volumes of data. Communications of the ACM, 39(11), 27-34.
Frawley, W. J., Piatetsky-Shapiro, G., & Matheus, C. J. (1992). Knowledge discovery in databases: An overview. AI magazine, 13(3), 57-57.
Gandhmal, D. P., & Kumar, K. (2019). Systematic analysis and review of stock market prediction techniques. Computer Science Review, 34, 100190.
Hagan, M., Demuth, H., & Beale, M. (1995). Neural network design, PWS Pub. Co., Boston, Mass., USA.
Hand, D. J., Mannila, H., & Smyth, P. (2001). Principles of data mining (adaptive computation and machine learning): MIT Press.
Helfert, E. A. (1972). Techniques of Financial Analysis, Homewood, Illinois: Richard D. Irwin. In: Inc.
Hoseinzade, E., & Haratizadeh, S. (2019). CNNpred: CNN-based stock market prediction using a diverse set of variables. Expert Systems with Applications, 129, 273-285.
Huang, W., Nakamori, Y., & Wang, S.-Y. (2005). Forecasting stock market movement direction with support vector machine. Computers & operations research, 32(10), 2513-2522.
Khaidem, L., Saha, S., & Dey, S. R. (2016). Predicting the direction of stock market prices using random forest. arXiv preprint arXiv:1605.00003.
Kumar, M., & Thenmozhi, M. (2006). Forecasting stock index movement: A comparison of support vector machines and random forest. Paper presented at the Indian institute of capital markets 9th capital markets conference paper.
Li, Z., Tam, V., & Yeung, L. (2016). Combining cloud computing, machine learning and heuristic optimization for investment opportunities forecasting. Paper presented at the 2016 IEEE Congress on Evolutionary Computation (CEC).
Liu, G., & Wang, X. (2019). A new metric for individual stock trend prediction. Engineering Applications of Artificial Intelligence, 82, 1-12.
Lui, Y.-H., & Mole, D. (1998). The use of fundamental and technical analyses by foreign exchange dealers: Hong Kong evidence. Journal of International money and Finance, 17(3), 535-545.
Murphy, J. J. (1999). Technical analysis of the financial markets: A comprehensive guide to trading methods and applications: Penguin.
Nelson, D. M., Pereira, A. C., & de Oliveira, R. A. (2017). Stock market's price movement prediction with LSTM neural networks. Paper presented at the 2017 International joint conference on neural networks (IJCNN).
Niaki, S. T. A., & Hoseinzade, S. (2013). Forecasting S&P 500 index using artificial neural networks and design of experiments. Journal of Industrial Engineering International, 9(1), 1.
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.
Pawar, K., Jalem, R. S., & Tiwari, V. (2019). Stock market price prediction using LSTM RNN. In Emerging Trends in Expert Applications and Security (pp. 493-503): Springer.
Piateski, G., & Frawley, W. (1991). Knowledge discovery in databases: MIT press.
Qiu, M., Song, Y., & Akagi, F. (2016). Application of artificial neural network for the prediction of stock market returns: The case of the Japanese stock market. Chaos, Solitons & Fractals, 85, 1-7.
Selvin, S., Vinayakumar, R., Gopalakrishnan, E., Menon, V. K., & Soman, K. (2017). Stock price prediction using LSTM, RNN and CNN-sliding window model. Paper presented at the 2017 international conference on advances in computing, communications and informatics (icacci).
Shynkevich, Y., McGinnity, T. M., Coleman, S. A., Belatreche, A., & Li, Y. (2017). Forecasting price movements using technical indicators: Investigating the impact of varying input window length. Neurocomputing, 264, 71-88.
Vanstone, B., & Finnie, G. (2009). An empirical methodology for developing stockmarket trading systems using artificial neural networks. Expert Systems with Applications, 36(3), 6668-6680.
Yang, J., Rao, R., Hong, P., & Ding, P. (2016). Ensemble model for stock price movement trend prediction on different investing periods. Paper presented at the 2016 12th International Conference on Computational Intelligence and Security (CIS).
Zhong, X., & Enke, D. (2017). Forecasting daily stock market return using dimensionality reduction. Expert Systems with Applications, 67, 126-139.


電子全文 電子全文(網際網路公開日期:20250827)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top