學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 使用機器學習選股之投資績效研究—台灣股票市場之實證
A Study on the Investment Performance of Machine Learning-Based Stock Selection — Empirical Evidence from the Taiwan Stock Market作者 許雅筑
Hsu, Ya-Chu貢獻者 吳啟銘
許雅筑
Hsu, Ya-Chu關鍵詞 機器學習
選股能力
股價預測
隨機森林模型
五分位數投資組合策略
投資組合績效
Machine Learning
Stock Selection Ability
Stock Price Prediction
Random Forest Model
Quintile Investment Portfolio Strategy
Portfolio Performance日期 2024 上傳時間 4-九月-2024 15:25:43 (UTC+8) 摘要 近年來機器學習已廣泛應用於金融領域，如何使用機器學習來幫助分析師捕捉隱含的訊息，已是許多學術及實務上的發展方向。因此，本文主要研究以人工智慧的機器學習法，應用於台灣股票市場的交易。本文運用個股過去的股票報酬率、交易周轉率與月營收年增率，應用隨機森林演算法預測未來可能上漲的股票作為投資標的，再搭配模型的特徵重要性來建構五分位數投資組合，並分為等權重與市值加權來進行分析。 實證顯示，依照排名的升高，投資組合的報酬跟風險也越大，風險調整後均有較佳的報酬，且可建構的年平均報酬率均高於市場投資組合的報酬率。透過三因子模型分析顯示，模型傾向於選擇投資小型股及成長股，而在排名最高的兩組等權重投資組合，均能獲得顯著正的超額報酬。 本研究實證顯示，機器學習對於投資策略與投資組合建構具有正面的影響，能夠幫助識別影響股價的重要因子，尋找隱含的訊息。這項研究能幫助投資人探索如何利用機器學習建構投資策略與投資組合。
In recent years, machine learning has been widely applied in the financial sector. How to use machine learning to help analysts capture implicit information has become a major direction for both academic and practical development. This study primarily investigates the application of machine learning, specifically artificial intelligence methods, in trading on the Taiwan stock market. By utilizing historical stock returns, turnover rates, and monthly revenue growth rates, this paper employs the random forest algorithm to predict stocks that are likely to rise in the future as investment targets. It further constructs quintile investment portfolios based on feature importance from the model, and analyzes them under both equal-weighted and market-cap-weighted schemes. Empirical results show that as the portfolio ranking increases, both returns and risks also increase. Adjusted for risk, the portfolios exhibit superior returns, with annual average returns outperforming the market portfolio. Analysis using the three-factor model indicates that the model tends to select small-cap and growth stocks. The top two quintile equal-weighted portfolios achieve significant positive excess returns. This study empirically demonstrates that machine learning has a positive impact on investment strategies and portfolio construction. It effectively aids in identifying key factors influencing stock prices and uncovering hidden information. This research can assist investors in exploring how to utilize machine learning to develop investment strategies and portfolios.參考文獻 一、中文部分 田鈜元 (2022)。以隨機森林法建構投資組合績效—以台灣股票市場為例。清華大學財務金融在職專班碩士論文。 沈佩璉 (2022)。機器學習於投資組合報酬率之影響。臺灣大學資訊管理學系碩士論文。 林生華 (2020)。機器學習因子擇時模型結合 Black-Litterman 模型之投資組合建構。政治大學金融學系碩士論文。 孫嘉蔚 (2021) 。運用機器學習模型分析影響公司風險的 ESG 因子：以台灣市場為例。政治大學金融學系碩士論文。 劉俞含 (2018)。XGBoost 模型、隨機森林模型、彈性網模型 於股價指數趨勢之預測—以台灣、日本、美國為例。中山大學財務管理學系碩士論文。 鄭仁杰 (2018)。利用隨機森林模型建構台灣指數期貨交易策略。政治大學金融學系碩士論文。 簡清源 (2022)。機器學習於投資組合之表現—隨機森林法的應用。元智大學管理學院博士班學位論文。 二、英文部分 Ahmed, S., Alshater, M. M., El Ammari, A., & Hammami, H. (2022). Artificial intelligence and machine learning in finance: A bibliometric review. Research in International Business and Finance, 61, 101646. 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. Bartram, S. M., Branke, J., De Rossi, G., & Motahari, M. (2021). Machine learning for active portfolio management. Journal of Financial Data Science, 3(3), 9-30. Breitung, C. (2023). Automated stock picking using random forests. Journal of Empirical Finance, 72, 532-556. Bustos, O., & Pomares-Quimbaya, A. (2020). Stock market movement forecast: A systematic review. Expert Systems with Applications, 156, 113464. Cao, K., & You, H. (2024). Fundamental Analysis via Machine Learning. Financial Analysts Journal, 80(2), 74-98. Fama, E. F., & French, K. R. (1993). Common risk factors in the returns on stocks and bonds. Journal of financial economics, 33(1), 3-56. Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223-2273. Huang, Y., Capretz, L. F., & Ho, D. (2021, December). Machine learning for stock prediction based on fundamental analysis. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 01-10). IEEE. Kumar, D., Sarangi, P. K., & Verma, R. (2022). A systematic review of stock market prediction using machine learning and statistical techniques. Materials Today: Proceedings, 49, 3187-3191. Kumbure, M. M., Lohrmann, C., Luukka, P., & Porras, J. (2022). Machine learning techniques and data for stock market forecasting: A literature review. Expert Systems with Applications, 197, 116659. Leippold, M., Wang, Q., & Zhou, W. (2022). Machine learning in the Chinese stock market. Journal of Financial Economics, 145(2), 64-82. Min, L., Dong, J., Liu, J., & Gong, X. (2021). Robust mean-risk portfolio optimization using machine learning-based trade-off parameter. Applied Soft Computing, 113, 107948. Pinelis, M., & Ruppert, D. (2022). Machine learning portfolio allocation. The Journal of Finance and Data Science, 8, 35-54. Plachel, L. (2019). A unified model for regularized and robust portfolio optimization. Journal of Economic Dynamics and Control, 109, 103779. Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The journal of finance, 19(3), 425-442. Tan, Z., Yan, Z., & Zhu, G. (2019). Stock selection with random forest: An exploitation of excess return in the Chinese stock market. Heliyon, 5(8). Vuong, P. H., Phu, L. H., Van Nguyen, T. H., Duy, L. N., Bao, P. T., & Trinh, T. D. (2024). A bibliometric literature review of stock price forecasting: from statistical model to deep learning approach. Science Progress, 107(1), 00368504241236557. Wolff, D., & Echterling, F. (2024). Stock picking with machine learning. Journal of Forecasting, 43(1), 81-102. Yuan, X., Yuan, J., Jiang, T., & Ain, Q. U. (2020). Integrated long-term stock selection models based on feature selection and machine learning algorithms for China stock market. IEEE Access, 8, 22672-22685. 描述 碩士
國立政治大學
財務管理學系
107357012資料來源 http://thesis.lib.nccu.edu.tw/record/#G0107357012 資料類型 thesis dc.contributor.advisor 吳啟銘 zh_TW dc.contributor.author (作者) 許雅筑 zh_TW dc.contributor.author (作者) Hsu, Ya-Chu en_US dc.creator (作者) 許雅筑 zh_TW dc.creator (作者) Hsu, Ya-Chu en_US dc.date (日期) 2024 en_US dc.date.accessioned 4-九月-2024 15:25:43 (UTC+8) - dc.date.available 4-九月-2024 15:25:43 (UTC+8) - dc.date.issued (上傳時間) 4-九月-2024 15:25:43 (UTC+8) - dc.identifier (其他 識別碼) G0107357012 en_US dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/153484 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 財務管理學系 zh_TW dc.description (描述) 107357012 zh_TW dc.description.abstract (摘要) 近年來機器學習已廣泛應用於金融領域，如何使用機器學習來幫助分析師捕捉隱含的訊息，已是許多學術及實務上的發展方向。因此，本文主要研究以人工智慧的機器學習法，應用於台灣股票市場的交易。本文運用個股過去的股票報酬率、交易周轉率與月營收年增率，應用隨機森林演算法預測未來可能上漲的股票作為投資標的，再搭配模型的特徵重要性來建構五分位數投資組合，並分為等權重與市值加權來進行分析。 實證顯示，依照排名的升高，投資組合的報酬跟風險也越大，風險調整後均有較佳的報酬，且可建構的年平均報酬率均高於市場投資組合的報酬率。透過三因子模型分析顯示，模型傾向於選擇投資小型股及成長股，而在排名最高的兩組等權重投資組合，均能獲得顯著正的超額報酬。 本研究實證顯示，機器學習對於投資策略與投資組合建構具有正面的影響，能夠幫助識別影響股價的重要因子，尋找隱含的訊息。這項研究能幫助投資人探索如何利用機器學習建構投資策略與投資組合。 zh_TW dc.description.abstract (摘要) In recent years, machine learning has been widely applied in the financial sector. How to use machine learning to help analysts capture implicit information has become a major direction for both academic and practical development. This study primarily investigates the application of machine learning, specifically artificial intelligence methods, in trading on the Taiwan stock market. By utilizing historical stock returns, turnover rates, and monthly revenue growth rates, this paper employs the random forest algorithm to predict stocks that are likely to rise in the future as investment targets. It further constructs quintile investment portfolios based on feature importance from the model, and analyzes them under both equal-weighted and market-cap-weighted schemes. Empirical results show that as the portfolio ranking increases, both returns and risks also increase. Adjusted for risk, the portfolios exhibit superior returns, with annual average returns outperforming the market portfolio. Analysis using the three-factor model indicates that the model tends to select small-cap and growth stocks. The top two quintile equal-weighted portfolios achieve significant positive excess returns. This study empirically demonstrates that machine learning has a positive impact on investment strategies and portfolio construction. It effectively aids in identifying key factors influencing stock prices and uncovering hidden information. This research can assist investors in exploring how to utilize machine learning to develop investment strategies and portfolios. en_US dc.description.tableofcontents 摘要 I Abstract II 目次 III 表次 IV 圖次 V 第一章 緒論 1 第一節 研究背景與動機 1 第二節 研究目的與貢獻 2 第三節 論文架構 4 第二章 文獻探討 5 第一節 利用機器學習建構投資組合 5 第二節 機器學習選股的權重配置方法 7 第三章 研究方法 8 第一節 研究流程 8 第二節 建構隨機森林模型 10 第三節 資料說明 18 第四節 建構投資組合 21 第五節 投資組合績效評估 24 第四章 實證結果分析 27 第一節 隨機森林預測效果 27 第二節 特徵變數篩選 29 第三節 投資組合績效評估 30 第五章 結論與建議 38 第一節 結論 38 第二節 研究限制與後續研究之建議 38 參考文獻 40 zh_TW dc.format.extent 2663454 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0107357012 en_US dc.subject (關鍵詞) 機器學習 zh_TW dc.subject (關鍵詞) 選股能力 zh_TW dc.subject (關鍵詞) 股價預測 zh_TW dc.subject (關鍵詞) 隨機森林模型 zh_TW dc.subject (關鍵詞) 五分位數投資組合策略 zh_TW dc.subject (關鍵詞) 投資組合績效 zh_TW dc.subject (關鍵詞) Machine Learning en_US dc.subject (關鍵詞) Stock Selection Ability en_US dc.subject (關鍵詞) Stock Price Prediction en_US dc.subject (關鍵詞) Random Forest Model en_US dc.subject (關鍵詞) Quintile Investment Portfolio Strategy en_US dc.subject (關鍵詞) Portfolio Performance en_US dc.title (題名) 使用機器學習選股之投資績效研究—台灣股票市場之實證 zh_TW dc.title (題名) A Study on the Investment Performance of Machine Learning-Based Stock Selection — Empirical Evidence from the Taiwan Stock Market en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 一、中文部分 田鈜元 (2022)。以隨機森林法建構投資組合績效—以台灣股票市場為例。清華大學財務金融在職專班碩士論文。 沈佩璉 (2022)。機器學習於投資組合報酬率之影響。臺灣大學資訊管理學系碩士論文。 林生華 (2020)。機器學習因子擇時模型結合 Black-Litterman 模型之投資組合建構。政治大學金融學系碩士論文。 孫嘉蔚 (2021) 。運用機器學習模型分析影響公司風險的 ESG 因子：以台灣市場為例。政治大學金融學系碩士論文。 劉俞含 (2018)。XGBoost 模型、隨機森林模型、彈性網模型 於股價指數趨勢之預測—以台灣、日本、美國為例。中山大學財務管理學系碩士論文。 鄭仁杰 (2018)。利用隨機森林模型建構台灣指數期貨交易策略。政治大學金融學系碩士論文。 簡清源 (2022)。機器學習於投資組合之表現—隨機森林法的應用。元智大學管理學院博士班學位論文。 二、英文部分 Ahmed, S., Alshater, M. M., El Ammari, A., & Hammami, H. (2022). Artificial intelligence and machine learning in finance: A bibliometric review. Research in International Business and Finance, 61, 101646. 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. Bartram, S. M., Branke, J., De Rossi, G., & Motahari, M. (2021). Machine learning for active portfolio management. Journal of Financial Data Science, 3(3), 9-30. Breitung, C. (2023). Automated stock picking using random forests. Journal of Empirical Finance, 72, 532-556. Bustos, O., & Pomares-Quimbaya, A. (2020). Stock market movement forecast: A systematic review. Expert Systems with Applications, 156, 113464. Cao, K., & You, H. (2024). Fundamental Analysis via Machine Learning. Financial Analysts Journal, 80(2), 74-98. Fama, E. F., & French, K. R. (1993). Common risk factors in the returns on stocks and bonds. Journal of financial economics, 33(1), 3-56. Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223-2273. Huang, Y., Capretz, L. F., & Ho, D. (2021, December). Machine learning for stock prediction based on fundamental analysis. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 01-10). IEEE. Kumar, D., Sarangi, P. K., & Verma, R. (2022). A systematic review of stock market prediction using machine learning and statistical techniques. Materials Today: Proceedings, 49, 3187-3191. Kumbure, M. M., Lohrmann, C., Luukka, P., & Porras, J. (2022). Machine learning techniques and data for stock market forecasting: A literature review. Expert Systems with Applications, 197, 116659. Leippold, M., Wang, Q., & Zhou, W. (2022). Machine learning in the Chinese stock market. Journal of Financial Economics, 145(2), 64-82. Min, L., Dong, J., Liu, J., & Gong, X. (2021). Robust mean-risk portfolio optimization using machine learning-based trade-off parameter. Applied Soft Computing, 113, 107948. Pinelis, M., & Ruppert, D. (2022). Machine learning portfolio allocation. The Journal of Finance and Data Science, 8, 35-54. Plachel, L. (2019). A unified model for regularized and robust portfolio optimization. Journal of Economic Dynamics and Control, 109, 103779. Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The journal of finance, 19(3), 425-442. Tan, Z., Yan, Z., & Zhu, G. (2019). Stock selection with random forest: An exploitation of excess return in the Chinese stock market. Heliyon, 5(8). Vuong, P. H., Phu, L. H., Van Nguyen, T. H., Duy, L. N., Bao, P. T., & Trinh, T. D. (2024). A bibliometric literature review of stock price forecasting: from statistical model to deep learning approach. Science Progress, 107(1), 00368504241236557. Wolff, D., & Echterling, F. (2024). Stock picking with machine learning. Journal of Forecasting, 43(1), 81-102. Yuan, X., Yuan, J., Jiang, T., & Ain, Q. U. (2020). Integrated long-term stock selection models based on feature selection and machine learning algorithms for China stock market. IEEE Access, 8, 22672-22685. zh_TW
