本篇論文將資訊科學領域之機器學習理論與財務領域之資產定價理論中的Fama-French三因子模型進行財務交易應用上的結合。本研究的發現主要有四點:
1. 與計量經濟學中常使用的羅吉斯迴歸(Logistic Regression)模型相比，其他機器學習模型預測準確率明顯提升，其中支持向量機(Support Vector Machine，SVM)預測準確率最高，隨機森林(Random Forest)次之。
2. 加入越多的因子，並無法因此提升預測準確率。即使透過機器學習模型進行預測，因子的選擇仍相當重要。
3. 訓練時間過短，將造成訓練資料及測試資料之預測準確率皆不準確。而在訓練期間足夠的情況下，測試時間縮短，對訓練資料準確率影響不大，但會改善測試資料準確率，呈現負相關的情形。
4. 透過本研究預測個股股價走勢之結果所建構的投資組合，在不考慮交易成本的情況下投資績效超越台灣加權股價指數之報酬率，但在考慮交易成本後則落後於大盤績效。然而，此投資組合的績效相對大盤平穩，在大盤大幅下跌時仍相對抗跌。

This study combines the Machine Learning Theory in the field of Computer Science with the Fama-French three-factor model of Asset Pricing Theory in the field of Finance for the application of financial transactions. There are four main findings of this study:

1. Compared with the Logistic Regression model, which is often used in econometrics, other machine learning models have significantly higher prediction accuracy, with the SVM model having the highest prediction accuracy and the Random Forest model is the second highest.
2. Adding more factors does not improve the prediction accuracy. The selection of factors is important.
3. If the training period is too short, the prediction accuracy of training data and test data will be inaccurate. If the training period is sufficient, the shortening of the test period will not have much effect on the accuracy of the training data, but will improve the accuracy of the test data, showing a negative correlation.
4. The portfolio constructed from the results of the study's predictions of stock price movements does not outperform the market return after considering the transaction costs. However, the performance of this portfolio is stable compared to the market.

Basak, S. et al. (2019). Predicting The Direction of Stock Market Prices Using Tree-based Classifiers. The North American Journal of Economics and Finance, 47, 552-567.
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, 663-682.
Da Z. & Warachka M.C. (2009). Cashflow Risk, Systematic Earnings Revisions, and the Cross-section of Stock Returns, Journal of Financial Economics 94, 448–468.
Fama, E. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 25(2), 383-417.
Fama, E. F. & French, K.R. (1993). Common Risk Factors In the Returns on Stocks and Bonds. Journal of Financial Economics, 33, 3-56.
Ferson, W.E., Harvey, C.R., (1994). Sources of Risk and Expected Returns in International Equity Markets. Journal of Banking and Finance 18, 775-803.
Gómez, J. P., R. Priestley, and F. Zapatero. (2012). Labor Income, Relative Wealth Concerns, and the Cross-section of Stock Returns, Journal of Financial and Quantitative Analysis. 51, 1111-1133.
Heo, J. and Yang, J. Y. (2016). Stock Price Prediction Based on Financial Statements Using SVM. International Journal of Hybrid Information Technology. 9, 57-66.
James, G., et al. (2013). An Introduction to Statistical Learning : with Applications in R.
Khaidem, L., Saha, S. & Dey, S.R. (2016). Predicting the Direction of Stock Market Prices Using Random Forest. Applied Mathematical Finance., April,2016, 1-21.
Kim, K. J. (2003). Financial Time Series Forecasting Using Support Vector Machines, Neurocomputing, Volume 55, Issues 1–2, 2003, 307-319.
Lewellen, J. (2015). The Cross-section of Expected Stock Returns. Critical Finance Review, 4, 1–44.
Lintner, J. (1965). The Valuation of Risk Assets and the Selection of Risky Investments in Stock Portfolios and Capital Budgets. Review of Economics and Statistics 47, 13-37.
New York :Springer.
Sharpe, W. (1964). Capital Asset Prices: A Theory of Market Equilibrium Under Conditions of Risk. Journal of Finance, 19, 425–442.
Welch, I., and A. Goyal. (2008). A Comprehensive Look At The Empirical Performance of Equity Premium Prediction. Review of Financial Studies, 21, 1455–508.
Xiu, D., et al. (2020). Empirical Asset Pricing via Machine Learning, The Review of Financial Studies, Volume 33, Issue 5, May 2020, 2223-2273
Yoo, P., Kim, M., & Jan, T. (2005). Machine Learning Techniques and Use of Event Information for Stock Market Prediction: A Survey and Evaluation. International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, 2, 835-841.