Trading Strategy and Portfolio Optimization using Support Vector Machine: An Empirical Study on the Stock Exchange of Thailand
Keywords:
Trading strategy, Portfolio optimization, Support vector machineAbstract
The trading in stock need many knowledge about financial factors which companies created index by using some methods for highest return but there is no information about how good of stock in each group and in this researsh used machine learning algorithm called Support Vector Machine for helping categorizing financial factors and create the probability number which represented of those factors in each group and the investors can use it for analyzing and creating there own portfolio. This researsh is aimed to develop portfolio by using Support Vector Machine for making easy usability in analyzing by investors.The Support Vector Machine will create score of each group in each stock, the high score on group can tell that the stock is good.There are 6 groups used such as valuation, profitability, growth, leverage, liquidity and operation.Every stock will have score on each group but it’s propably not same stock have high score on difference group,that’s why this score can tell how good on stock. The result shows score of 8 stocks with the highest score and the return on portfolio by selecting the stock from the result of score in each group.This will be the empirical that this score can easily use for making strategy by investors.
References
for stock prediction: Union, intersection, and multi-intersection approaches.
Decision Support Systems. 2010; 50(1): 258-269.
2. Thaler RH. The end of behavioral finance. Financial Analysts Journal.
1999; 55(6): 12-17.
3. Barberis N, Huang M. Mental accounting, loss aversion, and individual
stock returns. The Journal of Finance. 2001; 56(4): 1247-1292.
4. Enke D, Thawornwong S. The use of data mining and neural networks
for forecasting stock market returns. Expert Systems with Applications.
2005; 29(4): 927-940.
5. Cristianini N, Shawe-Taylor J. An introduction to support vector machines
and other Kernel-based learning methods. Cambridge, UK: Cambridge University
Press; 2000.
6. Zhang X, Hu Y, Xie K, Wang S, Ngai EWT, Liu M. A causal feature selection
algorithm for stock prediction modeling. Neurocomputing. 2014; 142: 48-59.
7. Yu H, Chen R, Zhang G. A SVM stock selection model within PCA. Procedia
Computer Science. 2014; 31: 406-412.
8. Fama EF. Efficient capital markets: A review of theory and empirical work.
The Journal of Finance. 1970; 25(2): 383-417.
9. Fama EF. Efficient capital markets: II. The Journal of Finance.
1991; 46(5): 1575-1617.
10. Huang C-L, Tsai C-Y. A hybrid SOFM-SVR with a filter-based feature
selection for stock market forecasting. Expert Systems with Applications.
2009; 36(2, Part 1): 1529-1539.
11. Yap BC-F, Mohamad Z, Chong K-R. The application of principal
component analysis in the selection of industry specific financial ratios.
British Journal of Economics, Management & Trade. 2013; 3(3): 242-252.
12. Patel J, Shah S, Thakkar P, Kotecha K. Predicting stock market index
using fusion of machine learning techniques. Expert Systems with
Applications. 2015; 42(4): 2162-2172.
13. Gerlein EA, McGinnity M, Belatreche A, Coleman S. Evaluating
machine learning classification for financial trading: An empirical
approach. Expert Systems with Applications. 2016; 54: 193-207.
14. Suteetasana S. Optimal technical trading rules on SET50 Index:
Support Vector Machine and econometrics approach. Faculty of
Commerce and Accountancy: Thammasat University; 2011.
