機器學習是透過統計推理過程的不斷訓練與測試數據來預測事件，近期在人臉識別、語音檢測、自動車駕駛等方面皆取得非常成功的應用，而在股票市場上則可以被運用於預測未來市場趨勢或是預測單一個股的報酬率。
本篇論文的主要目的是藉由機器學習的技術進行擇股應用，在眾多的機器學習模型中，向量支撐機器(SVM)可以有效對於二元問題進行分類，因此吾人利用SVM，結合特徵因子找出未來將會表現良好的股票，吾人透過三個與公司未來營運表現相關的觀點，來進行特徵因子的選擇，此外，亦提出三種進行標籤樣本的方法，並以模型準確率與接收者操作特徵曲線(ROC)相互比較。另外在SVM模型中，我們選擇徑向基函數核(RBF)進行非線性分類，因為它具備在沒有事先信息的情況下處理數據的良好特性，在整個訓練過程中，用於調整SVM參數的方法是使用網格搜索並進行五次交叉驗證。
鑑於基本特徵，投資者特徵和市場特徵，採用三種不同的標籤方式，吾人使用1998年至2011年期間資料訓練模型，並對2012年至2016年期間資料進行測試。測試績效顯示，利用向量支撐機器來進行擇股策略是有效果的，吾人亦比較，透過不同的標籤方式，年化報酬率在(19.30％，19.91％)範圍內，並且優於標普500指數與道瓊工業指數。此外，吾人亦使用濾嘴法則先篩選出基本面良好的股票，隨後進行訓練與測試，最後獲得(21.13％，21.82％)改善後的年化報酬率。

Machine Learning is a framework used to predict events through training and testing data in statistic inference. It has recently achieved successful application in face recognition, voice detection and the driving of automobiles, among others. It is also implemented in the stock market to predict whether the market is bullish or bearish.
The main purpose of this thesis is to implement the machine learning technique to select good stocks, and because SVMs (support vector machines) functionally work for classifying binary problems, we utilize an SVM to locate good stocks according to various features. Those features are chosen based on principles for selecting good stocks from three perspectives. Additionally, we propose three ways to label observations and compare them to each other based on their accuracy rate. The RBF kernel is implemented in the SVM because of its ability to cope with data lacking prior information. A five-fold cross-validation with a grid search is used as the method by which to tune the SVM parameters.
Given the fundamental features, investor features and market features with three different methods of labeling, we test the performance of returns in the period from 2012 to 2016 after training an SVM in the period from 1998 to 2011. There is significant evidence that utilizing SVMs to do stock selection is effective. The annualized returns are in the range of 19.30% and 19.91% according to the labeling method. Furthermore, we enhance our model with a filter rule and obtain the improved annualized returns in the range of 21.13% and 21.82%.

Beaver, W. H. (1966). Financial ratios as predictors of failure. Journal of accounting research, 4(1), 71-111.
Banz, R. W. (1981). The relationship between return and market value of common stocks. Journal of financial economics, 9(1), 3-18.
Barnes, P. (1987). The analysis and use of financial ratios: A review article. Journal of Business Finance & Accounting, 14(4), 449-461.
Barber, B. M., & Lyon, J. D. (1997). Detecting long-run abnormal stock returns: The empirical power and specification of test statistics. Journal of financial economics, 43(3), 341-372.
Burges, C. J. (1998). A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, 2(2), 121-167.
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(2), 281-305.
Cochrane, J. H. (1991). Production‐based asset pricing and the link between stock returns and economic fluctuations. The Journal of Finance, 46(1), 209-237.
Core, J. E., Holthausen, R. W., & Larcker, D. F. (1999). Corporate governance, chief executive officer compensation, and firm performance. Journal of financial economics, 51(3), 371-406.
Eliasson, M., Malik, K., & Österlund, B. (2011). A Value Relevant Fundamental Investment Strategy: The use of weighted fundamental signals to improve predictability.
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The journal of Finance, 25(2), 383-417.
Fama, E. F. (1995). Random walks in stock market prices. Financial analysts journal, 51(1), 75-80.
Fan, A., & Palaniswami, M. (2001). Stock selection using support vector machines. In Neural Networks, 2001. Proceedings. IJCNN'01. International Joint Conference on (Vol. 3, pp. 1793-1798). IEEE.
Gaspar, P., Carbonell, J., & Oliveira, J. L. (2012). On the parameter optimization of Support Vector Machines for binary classification. Journal of Integrative Bioinformatics (JIB), 9(3), 33-43.
Gompers, P. A., & Metrick, A. (2001). Institutional investors and equity prices. The quarterly journal of Economics, 116(1), 229-259.
Griffin, J. M., & Xu, J. (2009). How smart are the smart guys? A unique view from hedge fund stock holdings. Review of Financial Studies, 22(7), 2531-2570.
Hsu, C. W., Chang, C. C., & Lin, C. J. (2003). A practical guide to support vector classification.
Huang, W., Nakamori, Y., & Wang, S. Y. (2005). Forecasting stock market movement direction with support vector machine. Computers & Operations Research, 32(10), 2513-2522.
Kim, K. J. (2003). Financial time series forecasting using support vector machines. Neurocomputing, 55(1), 307-319.
Levine, R., & Zervos, S. (1998). Stock markets, banks, and economic growth. American economic review, 537-558.
Mantovani, R. G., Rossi, A. L., Vanschoren, J., Bischl, B., & Carvalho, A. C. (2015, July). To tune or not to tune: recommending when to adjust SVM hyper-parameters via Meta-learning. In Neural Networks (IJCNN), 2015 International Joint Conference on (pp. 1-8). IEEE.
Nayak, S. C., Misra, B. B., & Behera, H. S. (2014). Impact of data normalization on stock index forecasting. Int. J. Comp. Inf. Syst. Ind. Manag. Appl, 6, 357-369.
Ou, J. A., & Penman, S. H. (1989). Financial statement analysis and the prediction of stock returns. Journal of accounting and economics, 11(4), 295-329.
Piotroski, J. D. (2000). Value investing: The use of historical financial statement information to separate winners from losers. Journal of Accounting Research, 1-41.
Rosillo, R., Giner, J., & de la Fuente, D. (2014). The effectiveness of the combined use of VIX and Support Vector Machines on the prediction of S&P 500. Neural Computing and Applications, 25(2), 321-332.
Sloan, R. (1996). Do stock prices fully reflect information in accruals and cash flows about future earnings? (Digest summary). Accounting review, 71(3), 289-315.
Tay, F. E., & Cao, L. (2001). Application of support vector machines in financial time series forecasting. Omega, 29(4), 309-317.
Tay, F. E., & Cao, L. J. (2002). Modified support vector machines in financial time series forecasting. Neurocomputing, 48(1), 847-861.
Tang, L., & Lin, Q. (2016). Stock Selection Based on a Hybrid Quantitative Method. Open Journal of Statistics, 6(02), 346.
Vapnik, V. (2013). The nature of statistical learning theory. Springer science & business media.
Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann.
Zeileis, A., Hornik, K., Smola, A., & Karatzoglou, A. (2004). kernlab-an S4 package for kernel methods in R. Journal of statistical software, 11(9), 1-20.