學術產出-Theses
Article View/Open
Publication Export
-
題名 利用集成學習預測台灣加權股價指數漲跌
Applying Ensemble Learning to Enhance TAIEX Trend Prediction作者 陳羿妘
Chen, Yi-Yun貢獻者 黃泓智
Huang, Hong-Chih
陳羿妘
Chen, Yi-Yun關鍵詞 集成學習
羅吉斯迴歸
隨機森林
支持向量機
台灣加權股價指數
股價趨勢預測
Ensemble learning
Logistic regression
Random forest
Support vector machine
TAIEX
Stock trend prediction日期 2021 上傳時間 4-Aug-2021 14:55:15 (UTC+8) 摘要 本文旨在利用台灣加權股價指數TAIEX衍生之技術指標預測未來市場漲跌趨勢，藉由集成學習方法提升整體機器學習預測效果，結合羅吉斯迴歸、隨機森林、支持向量機三個異質演算法，增加模型間之差異性，並依據個別模型的特性，採用不同變數挑選方式，以提升資料品質，最終以單一模型作為標竿模型比較預測成效。整體而言，集成學習後之預測結果較單一模型具有更高的準確度，特別針對預測漲的部分，集成學習的效果較顯著，此外在長天期的趨勢預測中，集成學習的效果也更加明顯。
This study aims to enhance prediction of trends on TAIEX with ensemble learning. As the input, several technical indicators are selected to train the model. To increase diversity of ensemble model, we used three heterogeneous models (logistic regression, random forest, support vector machine) instead of homogeneous models as component learners. Besides, depends on characteristic of component learners, different methods of feature selection are applied to increase the quality of data. To evaluate performance of ensemble models, we used single classifier models as benchmark models, and we found that accuracy of ensemble models is higher than single models. Especially in long-term case, the improvement of ensemble learning is more significant.參考文獻 1. Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert systems with Applications, 42(20), 7046-7056.2. Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. The North American Journal of Economics and Finance, 47, 552-567.3. Di, X. (2014). Stock trend prediction with technical indicators using SVM. Independent Work Report, Stanford Univ.4. Dutta, A., Bandopadhyay, G., & Sengupta, S. (2012). Prediction of stock performance in the Indian stock market using logistic regression. International Journal of Business and Information, 7(1), 105.5. Jiang, M., Liu, J., Zhang, L., & Liu, C. (2020). An improved Stacking framework for stock index prediction by leveraging tree-based ensemble models and deep learning algorithms. Physica A: Statistical Mechanics and its Applications, 541, 122272.6. Kursa, M. B., & Rudnicki, W. R. (2010). Feature selection with the Boruta package. J Stat Softw, 36(11), 1-13.7. Li, H., Yang, Z., & Li, T. (2014). Algorithmic trading strategy based on massive data mining. Stanford University Stanford.8. Larsen, J. I. (2010). Predicting stock prices using technical analysis and machine learning (Master`s thesis, Institutt for datateknikk og informasjonsvitenskap).9. Moews, B., Herrmann, J. M., & Ibikunle, G. (2019). Lagged correlation-based deep learning for directional trend change prediction in financial time series. Expert Systems with Applications, 120, 197-206.10. Mierswa, I., & Morik, K. (2005). Automatic feature extraction for classifying audio data. Machine learning, 58(2), 127-149.11. Naik, N., & Mohan, B. R. (2019, May). Stock price movements classification using machine and deep learning techniques-the case study of indian stock market. In International Conference on Engineering Applications of Neural Networks (pp. 445-452). Springer, Cham.12. Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert systems with applications, 42(1), 259-268.13. Vapnik, V. N. (1995). The nature of statistical learning. Theory.14. Żbikowski, K. (2015). Using volume weighted support vector machines with walk forward testing and feature selection for the purpose of creating stock trading strategy. Expert Systems with Applications, 42(4), 1797-1805. 描述 碩士
國立政治大學
風險管理與保險學系
108358008資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108358008 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) 陳羿妘 zh_TW dc.contributor.author (Authors) Chen, Yi-Yun en_US dc.creator (作者) 陳羿妘 zh_TW dc.creator (作者) Chen, Yi-Yun en_US dc.date (日期) 2021 en_US dc.date.accessioned 4-Aug-2021 14:55:15 (UTC+8) - dc.date.available 4-Aug-2021 14:55:15 (UTC+8) - dc.date.issued (上傳時間) 4-Aug-2021 14:55:15 (UTC+8) - dc.identifier (Other Identifiers) G0108358008 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/136378 - 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) 108358008 zh_TW dc.description.abstract (摘要) 本文旨在利用台灣加權股價指數TAIEX衍生之技術指標預測未來市場漲跌趨勢，藉由集成學習方法提升整體機器學習預測效果，結合羅吉斯迴歸、隨機森林、支持向量機三個異質演算法，增加模型間之差異性，並依據個別模型的特性，採用不同變數挑選方式，以提升資料品質，最終以單一模型作為標竿模型比較預測成效。整體而言，集成學習後之預測結果較單一模型具有更高的準確度，特別針對預測漲的部分，集成學習的效果較顯著，此外在長天期的趨勢預測中，集成學習的效果也更加明顯。 zh_TW dc.description.abstract (摘要) This study aims to enhance prediction of trends on TAIEX with ensemble learning. As the input, several technical indicators are selected to train the model. To increase diversity of ensemble model, we used three heterogeneous models (logistic regression, random forest, support vector machine) instead of homogeneous models as component learners. Besides, depends on characteristic of component learners, different methods of feature selection are applied to increase the quality of data. To evaluate performance of ensemble models, we used single classifier models as benchmark models, and we found that accuracy of ensemble models is higher than single models. Especially in long-term case, the improvement of ensemble learning is more significant. 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 6第三節 研究流程 6第二章 文獻探討 8第一節 資料預處理 8第二節 特徵值挑選 9第三節 機器學習方法 9第三章 研究方法 12第一節 研究架構 12第二節 資料預處理 12第三節 特徵值挑選 23第四節 個別模型架構 24第五節 集成學習方法與建模流程 31第四章 實證結果 34第五章 結論與建議 42參考文獻 45附錄 48 zh_TW dc.format.extent 1034344 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108358008 en_US dc.subject (關鍵詞) 集成學習 zh_TW dc.subject (關鍵詞) 羅吉斯迴歸 zh_TW dc.subject (關鍵詞) 隨機森林 zh_TW dc.subject (關鍵詞) 支持向量機 zh_TW dc.subject (關鍵詞) 台灣加權股價指數 zh_TW dc.subject (關鍵詞) 股價趨勢預測 zh_TW dc.subject (關鍵詞) Ensemble learning en_US dc.subject (關鍵詞) Logistic regression en_US dc.subject (關鍵詞) Random forest en_US dc.subject (關鍵詞) Support vector machine en_US dc.subject (關鍵詞) TAIEX en_US dc.subject (關鍵詞) Stock trend prediction en_US dc.title (題名) 利用集成學習預測台灣加權股價指數漲跌 zh_TW dc.title (題名) Applying Ensemble Learning to Enhance TAIEX Trend Prediction en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1. Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert systems with Applications, 42(20), 7046-7056.2. Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. The North American Journal of Economics and Finance, 47, 552-567.3. Di, X. (2014). Stock trend prediction with technical indicators using SVM. Independent Work Report, Stanford Univ.4. Dutta, A., Bandopadhyay, G., & Sengupta, S. (2012). Prediction of stock performance in the Indian stock market using logistic regression. International Journal of Business and Information, 7(1), 105.5. Jiang, M., Liu, J., Zhang, L., & Liu, C. (2020). An improved Stacking framework for stock index prediction by leveraging tree-based ensemble models and deep learning algorithms. Physica A: Statistical Mechanics and its Applications, 541, 122272.6. Kursa, M. B., & Rudnicki, W. R. (2010). Feature selection with the Boruta package. J Stat Softw, 36(11), 1-13.7. Li, H., Yang, Z., & Li, T. (2014). Algorithmic trading strategy based on massive data mining. Stanford University Stanford.8. Larsen, J. I. (2010). Predicting stock prices using technical analysis and machine learning (Master`s thesis, Institutt for datateknikk og informasjonsvitenskap).9. Moews, B., Herrmann, J. M., & Ibikunle, G. (2019). Lagged correlation-based deep learning for directional trend change prediction in financial time series. Expert Systems with Applications, 120, 197-206.10. Mierswa, I., & Morik, K. (2005). Automatic feature extraction for classifying audio data. Machine learning, 58(2), 127-149.11. Naik, N., & Mohan, B. R. (2019, May). Stock price movements classification using machine and deep learning techniques-the case study of indian stock market. In International Conference on Engineering Applications of Neural Networks (pp. 445-452). Springer, Cham.12. Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert systems with applications, 42(1), 259-268.13. Vapnik, V. N. (1995). The nature of statistical learning. Theory.14. Żbikowski, K. (2015). Using volume weighted support vector machines with walk forward testing and feature selection for the purpose of creating stock trading strategy. Expert Systems with Applications, 42(4), 1797-1805. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202100893 en_US
