學術產出-Theses
Article View/Open
Publication Export
-
題名 利用集成學習建構股市最適投資組合
Using Ensemble Learning to Construct The Optimal Portfolio in Stock Market作者 林晏緯
Lin, Yen-Wei貢獻者 黃泓智
Huang, Hong-Chih
林晏緯
Lin, Yen-Wei關鍵詞 股市漲跌
集成學習
極限梯度提升
多層感知器
支持向量迴歸
Stock trend
Ensemble learning
XGBOOST
MLP
SVR日期 2021 上傳時間 4-Aug-2021 14:55:57 (UTC+8) 摘要 本研究使用台灣上市公司之財報資料以集成學習概念進行台灣股市個股漲跌預測，並建立最適投資組合。本研究使用多個不同的機器學習模型如極限梯度提升模型（XGBOOST）、多層感知器（MLP）、支持向量迴歸模型（SVR）等模型進行建模。為了使模型訓練結果更為穩定與準確，本研究使用上述模型進行多次訓練，選出各模型中上漲機率高的股票並對其進行綜合評分，接著組成股票投資清單，將評分高的股票進行權重配置建立投資組合。實證結果發現，相較於使用單一種模型做一次的訓練，使用多種模型進行多次訓練後建立的投資組合能夠有更穩定的結果，且整體績效也優於單一種模型。
This dissertation aims to use ensemble learning to predict the trend of stocks in Taiwan stock market and build an optimal portfolio. The machine learning models used in the study include XGBOOST, MLP, and SVR. To make the model training results more stable and accurate, this study uses the above models for multiple trainings, and selects the stocks with high rising probability in each model and rate each of them comprehensively. Consequently, the optimal portfolio is built by allocating stocks with high rating appropriately. The empirical results demonstrate that using several models which are trained for multiple times will lead to steadier outcome and greater performance compared to using single model.參考文獻 1. Alberg, J., & Lipton, Z. C. (2017). Improving factor-based quantitative investing by forecasting company fundamentals. arXiv preprint arXiv:1711.04837.2. 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. Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).4. Clarke, R. G., De Silva, H., & Thorley, S. (2006). Minimum-variance portfolios in the US equity market. The journal of portfolio management, 33(1), 10-24.5. Dietterich, T. G. (2002). Ensemble learning. The handbook of brain theory and neural networks, 2(1), 110-125.6. Emerson, S., Kennedy, R., O`Shea, L., & O`Brien, J. (2019, May). Trends and applications of machine learning in quantitative finance. In 8th international conference on economics and finance research (ICEFR 2019).7. Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric environment, 32(14-15), 2627-2636.8. Khaidem, L., Saha, S., & Dey, S. R. (2016). Predicting the direction of stock market prices using random forest. arXiv preprint arXiv:1605.00003.9. Markowitz, H. (1952). The utility of wealth. Journal of political Economy, 60(2), 151-158.10. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and computing, 14(3), 199-222.11. Tokat, Y., & Wicas, N. W. (2007). Portfolio rebalancing in theory and practice. The Journal of Investing, 16(2), 52-59. 描述 碩士
國立政治大學
風險管理與保險學系
108358026資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108358026 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) 林晏緯 zh_TW dc.contributor.author (Authors) Lin, Yen-Wei en_US dc.creator (作者) 林晏緯 zh_TW dc.creator (作者) Lin, Yen-Wei en_US dc.date (日期) 2021 en_US dc.date.accessioned 4-Aug-2021 14:55:57 (UTC+8) - dc.date.available 4-Aug-2021 14:55:57 (UTC+8) - dc.date.issued (上傳時間) 4-Aug-2021 14:55:57 (UTC+8) - dc.identifier (Other Identifiers) G0108358026 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/136381 - 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) 108358026 zh_TW dc.description.abstract (摘要) 本研究使用台灣上市公司之財報資料以集成學習概念進行台灣股市個股漲跌預測，並建立最適投資組合。本研究使用多個不同的機器學習模型如極限梯度提升模型（XGBOOST）、多層感知器（MLP）、支持向量迴歸模型（SVR）等模型進行建模。為了使模型訓練結果更為穩定與準確，本研究使用上述模型進行多次訓練，選出各模型中上漲機率高的股票並對其進行綜合評分，接著組成股票投資清單，將評分高的股票進行權重配置建立投資組合。實證結果發現，相較於使用單一種模型做一次的訓練，使用多種模型進行多次訓練後建立的投資組合能夠有更穩定的結果，且整體績效也優於單一種模型。 zh_TW dc.description.abstract (摘要) This dissertation aims to use ensemble learning to predict the trend of stocks in Taiwan stock market and build an optimal portfolio. The machine learning models used in the study include XGBOOST, MLP, and SVR. To make the model training results more stable and accurate, this study uses the above models for multiple trainings, and selects the stocks with high rising probability in each model and rate each of them comprehensively. Consequently, the optimal portfolio is built by allocating stocks with high rating appropriately. The empirical results demonstrate that using several models which are trained for multiple times will lead to steadier outcome and greater performance compared to using single model. en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究動機 1第二節 研究目的 2第三節 研究流程 3第二章 文獻探討 4第一節 機器學習模型文獻探討 4第二節 股價預測與機器學習模型文獻探討 5第三節 資產配置文獻探討 6第三章 研究方法 8第一節 研究架構 8第二節 財報變數篩選 10第三節 機器學習模型 13第四節 集成學習選股 22第五節 資產配置策略 25第六節 績效指標說明 27第四章 實證結果 28第一節 流動性篩選選股 28第二節 市值篩選選股 33第五章 結論與未來方向建議 38參考文獻 39 zh_TW dc.format.extent 1756638 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108358026 en_US dc.subject (關鍵詞) 股市漲跌 zh_TW dc.subject (關鍵詞) 集成學習 zh_TW dc.subject (關鍵詞) 極限梯度提升 zh_TW dc.subject (關鍵詞) 多層感知器 zh_TW dc.subject (關鍵詞) 支持向量迴歸 zh_TW dc.subject (關鍵詞) Stock trend en_US dc.subject (關鍵詞) Ensemble learning en_US dc.subject (關鍵詞) XGBOOST en_US dc.subject (關鍵詞) MLP en_US dc.subject (關鍵詞) SVR en_US dc.title (題名) 利用集成學習建構股市最適投資組合 zh_TW dc.title (題名) Using Ensemble Learning to Construct The Optimal Portfolio in Stock Market en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1. Alberg, J., & Lipton, Z. C. (2017). Improving factor-based quantitative investing by forecasting company fundamentals. arXiv preprint arXiv:1711.04837.2. 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. Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).4. Clarke, R. G., De Silva, H., & Thorley, S. (2006). Minimum-variance portfolios in the US equity market. The journal of portfolio management, 33(1), 10-24.5. Dietterich, T. G. (2002). Ensemble learning. The handbook of brain theory and neural networks, 2(1), 110-125.6. Emerson, S., Kennedy, R., O`Shea, L., & O`Brien, J. (2019, May). Trends and applications of machine learning in quantitative finance. In 8th international conference on economics and finance research (ICEFR 2019).7. Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric environment, 32(14-15), 2627-2636.8. Khaidem, L., Saha, S., & Dey, S. R. (2016). Predicting the direction of stock market prices using random forest. arXiv preprint arXiv:1605.00003.9. Markowitz, H. (1952). The utility of wealth. Journal of political Economy, 60(2), 151-158.10. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and computing, 14(3), 199-222.11. Tokat, Y., & Wicas, N. W. (2007). Portfolio rebalancing in theory and practice. The Journal of Investing, 16(2), 52-59. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202100851 en_US
