Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 結合基本面分析及集成學習模型建構最適投資組合
Combining Fundamental Analysis and Ensemble Learning to Construct the Optimal Portfolio
作者 許育愷
Hsu, Yu-Kai
貢獻者 黃泓智
許育愷
Hsu, Yu-Kai
關鍵詞 基本面分析
集成學習
支持向量回歸模型
多層感知器
報酬率預測
投資組合
Fundamental Analysis
Ensemble Learning
SVR
MLP
Return Predict
Portfolio
日期 2021
上傳時間 4-Aug-2021 14:55:43 (UTC+8)
摘要 本研究透過結合基本面分析以及集成學習的方式,在上市個股當中建立最適的投資組合,首先藉由兩個基本面的因子:本益比(PE Ratio)與股價淨值比(PB Ratio)篩選個股,接著,藉由包含支持向量迴歸模型(SVR)及多層感知器(MLP)的集成學習模型預測個股的數日後報酬,藉此挖掘出有潛力的個股進行投資組合的配置,並藉由歷史回測分析其績效。實驗結果顯示,在基本面篩選下的投資組合績效高於大盤指數績效,而加入集成學習模型後可以進一步提升其報酬績效。
The purpose of this study is trying to combine fundamental analysis and ensemble learning model to construct an optimal portfolio with listed stocks. First, use two fundamental factor, price-to-equity ratio and price-to-book ratio, to select potential stocks, and then predict the future return of each stock through ensemble learning model which including SVR and MLP to construct an optimal portfolio. Finally, analysis the performance according history stock data. The result shows that the portfolio constructed by only fundamental analysis outperforms Taiwan Capitalization Weighted Stock Index (TAIEX), and the portfolio constructed by fundamental analysis and ensemble learning outperforms the portfolio constructed by only fundamental analysis.
參考文獻 1. 張家瑋(2017)。利用籌碼面分析與關聯規則建構最適投資組合。國立政治大學碩士論文。
2. 蕭鈞銓(2016)。以基本面分析建構最適資產配置流程。國立政治大學碩士論文。
3. Basu, S. (1977). Investment performance of common stocks in relation to their price‐earnings ratios: A test of the efficient market hypothesis. The journal of Finance, 32(3), 663-682.
4. Chan, L. K., Hamao, Y., & Lakonishok, J. (1991). Fundamentals and stock returns in Japan. The journal of finance, 46(5), 1739-1764.
5. Clemen, R. T. (1989). Combining forecasts: A review and annotated bibliography. International journal of forecasting, 5(4), 559-583.
6. Hegazy, O., Soliman, O. S., & Salam, M. A. (2014). A machine learning model for stock market prediction. International Journal of Computer Science and Telecommunications, 4(12), 17-23
7. Huang, C. S., & Liu, Y. S. (2019). Machine Learning on Stock Price Movement Forecast: The Sample of the Taiwan Stock Exchange. International Journal of Economics and Financial Issues, 9(2), 189-201.
8. Lev, B., & Thiagarajan, S. R. (1993). Fundamental Information Analysis. Journal of Accounting Research, 31(2), 190–215.
9. Markowitz H., (1952). Portfolio Selection. The Journal of Finance, 7(1), 77–91.
10. Mangalampalli, R., Pandey, V., Khetre, P., & Malviya, V. (2020). Stock Prediction using Hybrid ARIMA and GRU Models. International Journal of Engineering Research & Technology, 9(5), 737-743.
11. Sharpe, W. F. (1966). Mutual fund performance. The Journal of business, 39(1), 119-138.
12. Zhang, J., Li, L., & Chen, W. (2020). Predicting stock price using two-stage machine learning techniques. Computational Economics, 1-25.
描述 碩士
國立政治大學
風險管理與保險學系
108358025
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108358025
資料類型 thesis
dc.contributor.advisor 黃泓智zh_TW
dc.contributor.author (Authors) 許育愷zh_TW
dc.contributor.author (Authors) Hsu, Yu-Kaien_US
dc.creator (作者) 許育愷zh_TW
dc.creator (作者) Hsu, Yu-Kaien_US
dc.date (日期) 2021en_US
dc.date.accessioned 4-Aug-2021 14:55:43 (UTC+8)-
dc.date.available 4-Aug-2021 14:55:43 (UTC+8)-
dc.date.issued (上傳時間) 4-Aug-2021 14:55:43 (UTC+8)-
dc.identifier (Other Identifiers) G0108358025en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/136380-
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) 108358025zh_TW
dc.description.abstract (摘要) 本研究透過結合基本面分析以及集成學習的方式,在上市個股當中建立最適的投資組合,首先藉由兩個基本面的因子:本益比(PE Ratio)與股價淨值比(PB Ratio)篩選個股,接著,藉由包含支持向量迴歸模型(SVR)及多層感知器(MLP)的集成學習模型預測個股的數日後報酬,藉此挖掘出有潛力的個股進行投資組合的配置,並藉由歷史回測分析其績效。實驗結果顯示,在基本面篩選下的投資組合績效高於大盤指數績效,而加入集成學習模型後可以進一步提升其報酬績效。zh_TW
dc.description.abstract (摘要) The purpose of this study is trying to combine fundamental analysis and ensemble learning model to construct an optimal portfolio with listed stocks. First, use two fundamental factor, price-to-equity ratio and price-to-book ratio, to select potential stocks, and then predict the future return of each stock through ensemble learning model which including SVR and MLP to construct an optimal portfolio. Finally, analysis the performance according history stock data. The result shows that the portfolio constructed by only fundamental analysis outperforms Taiwan Capitalization Weighted Stock Index (TAIEX), and the portfolio constructed by fundamental analysis and ensemble learning outperforms the portfolio constructed by only fundamental analysis.en_US
dc.description.tableofcontents 第一章 緒論 6
第一節 研究動機 6
第二節 研究目的 7
第三節 研究流程 7
第二章 文獻回顧 9
第一節 投資組合文獻探討 9
第二節 基本面分析文獻探討 10
第三節 集成學習文獻探討 10
第三章 研究方法 12
第一節 研究架構 12
第二節 基本面篩選 13
第三節 集成學習模型 16
第四節 權重配置方法 23
第五節 績效分析指標 24
第四章 實證分析 26
第一節 SVR_MLP模型實證結果 26
第二節 5MLP模型實證結果 28
第三節 SMX模型實證結果 30
第五章 結論與建議 32
參考文獻 33
zh_TW
dc.format.extent 1461680 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108358025en_US
dc.subject (關鍵詞) 基本面分析zh_TW
dc.subject (關鍵詞) 集成學習zh_TW
dc.subject (關鍵詞) 支持向量回歸模型zh_TW
dc.subject (關鍵詞) 多層感知器zh_TW
dc.subject (關鍵詞) 報酬率預測zh_TW
dc.subject (關鍵詞) 投資組合zh_TW
dc.subject (關鍵詞) Fundamental Analysisen_US
dc.subject (關鍵詞) Ensemble Learningen_US
dc.subject (關鍵詞) SVRen_US
dc.subject (關鍵詞) MLPen_US
dc.subject (關鍵詞) Return Predicten_US
dc.subject (關鍵詞) Portfolioen_US
dc.title (題名) 結合基本面分析及集成學習模型建構最適投資組合zh_TW
dc.title (題名) Combining Fundamental Analysis and Ensemble Learning to Construct the Optimal Portfolioen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) 1. 張家瑋(2017)。利用籌碼面分析與關聯規則建構最適投資組合。國立政治大學碩士論文。
2. 蕭鈞銓(2016)。以基本面分析建構最適資產配置流程。國立政治大學碩士論文。
3. Basu, S. (1977). Investment performance of common stocks in relation to their price‐earnings ratios: A test of the efficient market hypothesis. The journal of Finance, 32(3), 663-682.
4. Chan, L. K., Hamao, Y., & Lakonishok, J. (1991). Fundamentals and stock returns in Japan. The journal of finance, 46(5), 1739-1764.
5. Clemen, R. T. (1989). Combining forecasts: A review and annotated bibliography. International journal of forecasting, 5(4), 559-583.
6. Hegazy, O., Soliman, O. S., & Salam, M. A. (2014). A machine learning model for stock market prediction. International Journal of Computer Science and Telecommunications, 4(12), 17-23
7. Huang, C. S., & Liu, Y. S. (2019). Machine Learning on Stock Price Movement Forecast: The Sample of the Taiwan Stock Exchange. International Journal of Economics and Financial Issues, 9(2), 189-201.
8. Lev, B., & Thiagarajan, S. R. (1993). Fundamental Information Analysis. Journal of Accounting Research, 31(2), 190–215.
9. Markowitz H., (1952). Portfolio Selection. The Journal of Finance, 7(1), 77–91.
10. Mangalampalli, R., Pandey, V., Khetre, P., & Malviya, V. (2020). Stock Prediction using Hybrid ARIMA and GRU Models. International Journal of Engineering Research & Technology, 9(5), 737-743.
11. Sharpe, W. F. (1966). Mutual fund performance. The Journal of business, 39(1), 119-138.
12. Zhang, J., Li, L., & Chen, W. (2020). Predicting stock price using two-stage machine learning techniques. Computational Economics, 1-25.
zh_TW
dc.identifier.doi (DOI) 10.6814/NCCU202100808en_US