(44.192.10.166) 您好!臺灣時間:2021/03/06 04:00
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:王皓
研究生(外文):Wang, Hao
論文名稱:集成學習與主成分分析於股票指數之應用
論文名稱(外文):Application of Ensemble Learning with Principal Component Analysis in Stock Indices
指導教授:黃宜侯黃宜侯引用關係
指導教授(外文):Huang, Yi-Hou
口試委員:黃宜侯梁婉麗王衍智詹佳縈
口試委員(外文):Huang, Yi-HouLiang, Woan-lihWang, Yan-ZhiChan, Chia-Ying
口試日期:2019-06-18
學位類別:碩士
校院名稱:國立交通大學
系所名稱:財務金融研究所
學門:商業及管理學門
學類:財務金融學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:56
中文關鍵詞:機器學習集成學習指數預測
外文關鍵詞:machine learningensemble learningstock indicesprediction
相關次數:
  • 被引用被引用:0
  • 點閱點閱:61
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
過去已有許多研究探討資產價格的預測性,其中有一部份的學者以技術指標作為傳統回歸之獨立變數,並得到了顯著的預測性。而近年來在機器學習技術發展之下,已經越來越支持更高維度的非線性回歸計算,因此本篇論文將採用三種非線性回歸: 支持向量機、隨機森林、遞歸神經網路做預測。而為了讓預測結果更好,此篇論文使用集成學習將此三種模型整合。相較於前人之研究,此篇論文使用的特徵除了技術指標外,我們額外加入了指數期貨與指數選擇權的指標。並且,本篇論文的研究對象擴展至8種指數,研究年限擴時西元1996年至2016年。而除了預測外,本篇論文也建構一個交易策略,實證結果發現遞歸神經網路以及集成學習皆能戰勝大盤,其中以集成學習績效最好,這也驗證了集成學習在預測方面有很好的表現。
Previous studies have been devoted to the predictability of the asset price. Some researchers used technical indicators as independent variables to conduct the ordinary least square, and they get the significant predictability. Recently, the development of the machine learning allows us to conduct regression in higher dimension. This paper conduct three non-linear model: support vector regression, random forest and recurrent neural network. In order to enhance the predictability of the models, we apply ensemble learning to combine the result. Compare to other researches, we not only use the technical indicators, but also consider the features of indices futures and options. In addition, we expand our target indices to 9 kinds of indices and lengthen investigation timeline to 20 years. Besides prediction, we also build a trading strategy, and we find that both recurrent neural network and ensemble learning can beat the market, where ensemble learning methods brings the highest return, and this demonstrates the predictability of the ensemble learning skills.
Table of Contents
Chinese Abstract iii
English Abstract iv
Table of Contents v
List of Tables vii
List of Figures viii
1. Introduction 1
1.1 General Background Information 1
1.2 Purpose of Research 2
1.3 Research Contribution 2
2. Literature Review 4
2.1 Development of ensemble learning 4
2.2 Models for Prediction 6
3. Data Preprocessing 9
3.1 Data Source 9
3.1.1 Taiwan Capitalization Weighted Index (TAIEX) 9
3.1.2 Taiwan Financial Index (TWFF) 9
3.1.3 Taiwan Electronic Index (TWFE) 10
3.1.4 CSI300 Index 10
3.1.5 CSI500 Index 11
3.1.6 SSE50 Index 12
3.1.7 Dow Jones Industrial Average (DJIA) 12
3.1.8 NASDAQ Composite Index 13
3.2 Preprocessing of time series data 13
3.3 Feature extraction 13
3.3.1 Technical indicators 14
3.3.2 Futures features 18
3.3.3 Options features 19
3.4 Measurement of performance 19
3.5 Summary statistic 20
4. Methodology 22
4.1 Model of prediction 22
4.1.1 Support Vector Regression (SVR) 22
4.1.2 Random Forest (RF) 25
4.1.3 Recurrent Neural Network (RNN) 27
4.2 Principal Component Analysis (PCA) 28
4.3 Model combination 29
4.3.1 Bagging 29
4.3.2 Boosting 30
5. Prediction results 32
5.1 Study process 32
5.2 Comparison of single models 32
5.3 Ensemble learning 33
5.4 Principle Component Analysis 33
5.5 Trading strategy 34
6. Conclusion 35
References 37

List of Tables
Table 1: variables and descriptions 39
Table 2: summary statistic 40
Table 2.1: Chande Momentum Oscillator 40
Table 2.2: Trend Detection Index 40
Table 2.3: Vertical Horizontal Filter 40
Table 2.4: Exponential Moving Average 41
Table 2.5: Know Sure Thing 41
Table 2.6: William’s %R 41
Table 2.7: Relative Strength Index 41
Table 2.8: Moving Average Convergence/ Divergence 42
Table 2.9: Chakin Volatility 42
Table 2.10: Bolling Bands %B 42
Table 2.11: Average True Range 42
Table 3: prediction results 43
Table 3.1: MAE 43
Table 3.2: RMSE 43
Table 3.3: DS 43

List of Figures
Figure 1: the process of Bagging 4
Figure 2: the process of boosting 6
Figure 3: the concept of margin 22
Figure 4: example of linearly separable case 23
Figure 5: example of decision tree 27
Figure 6: structure of recurrent neural network 27
Figure 7: the study process of the research 32
Figure 8: the binary comparison in TAIEX 44
Figure 9: the distribution of actual price and price predicted by single model 45
Figure 10: the distribution of actual price and price predicted by ensemble learning 46
Figure 11: the distribution of actual price and price predicted after PCA 47
Figure 12: the cumulative gain 48
1. Aydogmus, H., Ekinci, A., Erdal, H.I., Erdal, H., 2015. Optimizing the monthly crude oil price forecasting accuracy via bagging ensemble models. Journal of Economics and International Finance, 7, 127-136.
2. Booth, A., Gerding, E., McGroarty, F., 2015. Performance-weighted ensembles of random forests for predicting price impact. Quantitative Finance, 15, 1823-1835.
3. Booth, A., Gerding, E., McGroarty, F., 2014. Automated trading with performance weighted random forests and seasonality. Expert Systems with Applications, 41, 3651-3661.
4. Breiman, L., 1996. Bagging predictors. Machine Learning, 26, 123-140.
5. Breiman, L., 2001. Random forests. Machine Learning, 45, 5-32.
6. Brock, W., Lakonishok, J., LeBaron, B., 1992. Simple technical trading rules and the stochastic properties of stock returns. Journal of Finance, 47, 1731-1764.
7. Cao, L.J., Tay, F.E.H.,2003. Support vector machine with adaptive parameters in financial time series forecasting. IEEE Transactions on neural networks, 14, 1506-1518.
8. Chen, K.Y., Ho C.H., 2007. An improved support vector regression modeling for Taiwan stock exchange market weighted index forecasting. EvoWorkshops, 4448, 169-178.
9. Contreras, J., Espinola, R., Nogales, F.J., Conejo, A.J., 2003. ARIMA models to predict next-day electricity prices. IEEE Transactions on Power Systems, 18, 1014-1020.
10. Cortes, C., Vapnik, V., 1995. Support-vector network. Machine Learning, 20, 273-297.
11. Cowles, A., 1933. Can stock market forecasters forecast? Econometrica, 1, 309-324.
12. Drucker, H., Burges, C.J., Kaufman, L., Smola, A., Vapnik, V., 1997. Support vector regression machines. Neural Information Processing Systems, 9, 155-161.
13. Freund, Y., 1992. An improved boosting algorithm and its implications on learning complexity. In Proceedings of COLT, 92, 391-398.
14. Freund, Y., Schapire, R.E., 1996. Experiments with a new boosting algorithm. International Conference on Machine Learning, 96, 148-156.
15. Funahashi, K., Nakamura, Y., 1993. Approximation of dynamical systems by continuous-time recurrent neural network. Neural Networks, 6, 801-806.
16. Goh, J., Jiang, F., Tu, J., Zhou, G., 2013. Forecasting Government Bond Risk Premia using Technical Indicators. Singapore Management University and Washington University in St. Louis (Working Paper).
17. Grigoryan, H., 2016. A stock market prediction method based on support vector machines (SVM) and independent component analysis (ICA). Database Systems Journal, 7, 12-21.
18. Guo, Z., Wang, H., Liu, Q., Yang, J., 2014. A feature fusion based forecasting model for financial time series. Public Library of Science One, 9, 1-13.
19. Liu, Z.P., Wu, L.Y., Wang, Y., Zhang, X.S., Chen, L., 2010. Prediction of protein-RNA binding sites by features. Bioinformatics, 26, 1616-1622.
20. Lo, A.W., Mamaysky, H., Wang, J., 2000. Foundation of technical analysis: computational algorithm, statistical inference, and empirical implementation. Journal of Finance, 55, 1705-1770.
21. Nochai, R., Nochai, T., 2006. ARIMA model for forecasting oil palm price. In Proceedings of the 2nd IMT-GT Regional conference on Mathematics. Statistics and Application, 13-15.
22. Pascanu, R., Mikolov, T., Bengio, Y., 2013. On the difficulty of training recurrent neural networks. In Proceedings of the 30th International Conference on Machine Learning, 1310-1318.
23. Saad, E.W., Prokhorov, D.V., Wunsch, D.C., 1998. Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks. IEEE Transactions on Neural Networks, 9, 1456-70.
24. Schapire, R.,1990. The strength of weak learnability. Machine Learning, 5, 197-226.
25. Valiant, L. G.,1984. A theory of the learnable. Communications of the ACM, 27, 1134-1142.
26. Wu, T., McCallum, A., 2005. Do oil futures prices help predict future oil prices. FRBSF Economic Letter, 38.
27. Yoon, Y., Swales, G., Margavio, T.M., 1993. A comparison of discriminant analysis versus artificial neural networks. Journal of the Operational Research Society, 44, 51-60.
電子全文 電子全文(網際網路公開日期:20220626)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔