BUILDING MULTI-FACTOR STOCK SELECTION SYSTEM USING MIXTURE DESIGN AND NEURAL NETWORKS

10.6338/JDA.201808_13(4).0001

I-Cheng Yeh；Tzu-Kuang Hsu；Jeng-Xiang Yen；Chin-Chang Tsai

stock market ； stock selection ； multi-factor model ； design of experiment ； neural network ； optimization

Journal of Data Analysis

13卷4期（2018 / 08 / 01）

1 - 27

英文

Over the past most multi-factor stock selection models used score approach, and subjectively set the score weight for each factor. This subjective approach not only cannot optimize performance of stock selection model, but also cannot determine the best weights in accordance with the preferences of investors. This study employed mixture design of experiment and neural networks to construct stock investment decision-making system to overcome these shortcomings. Using six stock selection concepts, small price to book value ratio (PBR), large return on equity (ROE), large annual revenue growth rate during recent three months, large current quarter return, large total market capitalization, and small systematic risk β, and a mixture design of experiment called Simplex Centroid Design, 63 experiment points were generated. The samples of this study contain all listed stocks on Taiwan stock market, and the study period is from 1997 to 2009 with a total of 13 years. The results showed that (1) in the annual rate of return prediction model, the large ROE concept representing growth and the small PBR concept representing the value were the most important predictors. (2) In the standard deviation of annual rate of return prediction model, the small PBR concept and the small β concept were the most important predictors, and revealed that the smaller the current risk, the smaller the future risk. The risk of equity is persistent. (3) The empirical results showed that the stock selection strategies generated by the optimization models could meet various preferences of investors.

1. Asness, C. S.,Moskowitz, T. J.,Pedersen, L. H.(2013).Value and momentum everywhere.Journal of Finance,68(3),929-985.
2. Atsalakis, G. S.,Valavanis, K. P.(2009).Surveying stock market forecasting techniques - Part II: Soft computing methods.Expert Systems with Applications,36(3),5932-5941.
3. Banz, R.W.(1981).The relationship between return and market value of common stocks.Journal of Financial Economics,9(1),3-18.
4. Bodie, Z.,Kane, A.,Marcus, A. J.(2011).Investment and portfolio management.New York:McGraw-Hill Irwin.
5. Cao, Q.,Leggio, K. B.,Schniederjans, M. J.(2005).A comparison between Fama and French's model and artificial neural networks in predicting the Chinese stock market.Computers and Operations Research,32(10),2499-2512.
6. CMoney (2012). http://www.cmoney.tw/
7. De Bondt, W.,Thaler, R. H.(1985).Does the stock market overreact?.Journal of Finance,40(3),793-805.
8. Duran-Vazquez, R.,Lorenzo-Valdes, A.,Castillo-Ramirez, C. E.(2014).Effectiveness of corporate finance valuation methods: Piotroski score in an Ohlson model: the case of Mexico.Journal of Economics Finance and Administrative Science,19(37),104-107.
9. Eakins, S. G.,Stansell, S. R.(2003).Can value-based stock selection criteria yield superior risk-adjusted returns: an application of neural networks.International Review of Financial Analysis,12(1),83-97.
10. Fama, E.,French, K.(1998).Value versus growth: the international evidence.Journal of Finance,53(6),1975-2000.
11. Guerard, J. B., Jr,Markowitz, H.,Xu, G.(2015).Earnings forecasting in a global stock selection model and efficient portfolio construction and management.International Journal of Forecasting,31(2),550-560.
12. Hadavandi, E.,Shavandi, H.,Ghanbari, A.(2010).Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting.Knowledge-Based Systems,23(8),800-808.
13. Hart, J.,Slagter, E.,Dijk, D.(2003).Stock selection strategies in emerging markets.Journal of Empirical Finance,10(1),105-132.
14. Haykin, S.(2008).Neural Networks and Learning Machines.Prentice Hall.
15. Holthausen, R.,Larker, D.(1992).The prediction of stock returns using financial statement information.Journal of Accounting and Economics,15(2),373-411.
16. Hong, H.,Lim, T.,Stein, J. C.(2000).Bad news travels slowly: size, analyst coverage, and the profitability of momentum strategies.Journal of Finance,55(1),265-295.
17. Huang, C. F.(2012).A hybrid stock selection model using genetic algorithms and support vector regression.Applied Soft Computing,12(2),807-818.
18. Huang, C. F.,Hsieh, T. N.,Rong Chang, B.,Chang, C. H.(2014).A study of risk-adjusted stock selection models using genetic algorithms.Engineering Computations,31(8),1720-1731.
19. Jegadeesh, N.,Titman, S.(1993).Returns to buying winners and selling losers: implications for stock market efficiency.Journal of Finance,48(1),65-91.
20. Kang, J.,Ding, D.(2005).Value and Growth Investing in Asian Stock Markets 1991-2002.Research in Finance,22,113-139.
21. Kim, S.,Lee, C.(2014).Implementability of trading strategies based on accounting information: Piotroski (2000) revisited.European Accounting Review,23(4),553-558.
22. Liu, Y. C.,Yeh, I. C.(2017).Using mixture design and neural networks to build stock selection decision support systems.Neural Computing and Applications,28(3),521-535.
23. Mohanram, S.(2005).Separating winners from losers among low book-to-market stocks using financial statement analysis.Review of Accounting Studies,10(2-3),133-170.
24. Montgomery, D. C.(2012).Design and Analysis of Experiments.New York:John Wiley and Sons, Inc.
25. Moreno, D.,Olmeda, I.(2007).Is the predictability of emerging and developed stock markets really exploitable?.European Journal of Operational Research,182(1),436-454.
26. Myers, R.H.,Montgomery, D.C.(2008).Response Surface Methodology.New York:John Wiley and Sons, Inc..
27. Nocedal, J.,Wright, S. J.(1999).Numerical optimization.New York:Springer.
28. Olson, D.,Mossman, C.(2003).Neural network forecasts of Canadian stock returns using accounting ratios.International Journal of Forecasting,19(3),453-465.
29. Piotroski, J.(2000).Value investing: the use of historical financial statement information to separate winners from losers.Journal of Accounting Research,38(1),1-41.
30. Ponsich, A.,Jaimes, A. L.,Coello, C. A. C.(2013).A survey on multiobjective evolutionary algorithms for the solution of the portfolio optimization problem and other finance and economics applications.IEEE Transactions on Evolutionary Computation,17(3),321-344.
31. Qian, E. E.,Hua, R. H.,Sorensen, E. H.(2007).Quantitative equity portfolio management: modern techniques and applications.Chapman and Hall/CRC.
32. Ren, N.,Zargham, M.,Rahimi, S.(2006).A decision tree-based classification approach to rule extraction for security analysis.International Journal of Information Technology and Decision Making,5(1),227-240.
33. Roko, I.,Gilli, M.(2008).Using economic and financial information for stock selection.Computational Management Science,5(4),317-335.
34. Sorensen, E.,Miller, K.,Ooi, C.(2000).The decision tree approach to stock selection.Journal of Portfolio Management,27(1),42-52.
35. Yeh, I. C.,Cheng, W. L.(2010).First and second order sensitivity analysis of MLP.Neurocomputing,73(10),2225-2233.
36. Yeh, I. C.,Hsu, T. K.(2011).Growth value two-factor model.Journal of Asset Management,11(6),435-451.
37. Yeh, I. C.,Lien, C. H.(2017).Growth and value hybrid valuation model based on mean reversion.Applied Economics,49(50),5092-5116.
38. Zhang, R.,Lin, Z. A.,Chen, S.,Zhao, M.,Yuan, M.(2018).Adaboost-SVM Multi-Factor Stock Selection Model Based on Adaboost Enhancement.International Journal of Statistics and Probability,7(5),9-18.