Affiliations: [a]
School of Business, Zhejiang Wanli University, Ningbo, China
| [b]
School of Information, Ningbo University of Finance & Economics, Ningbo, China
| [c]
School of Management Science and Engineering, Nanjing University of Finance and Economics, Xixia District, Nanjing, China
Correspondence:
[*]
Corresponding author. Tiejun Pan, School of Information, Ningbo University of Finance & Economics, No. 899 Xueyuan Rd, 315175, Ningbo, China. E-mails: [email protected]; [email protected].
Abstract: Quantitative Trading based on Machine Learning can increase the stock exchanging competitive and further enhance stability in the Chinese financial market, while the Risk to income ratio in the A share sector haven’t been studied well enough so far in the Quantitative Trading. The paper study the risk and opportunity in the Chinese share market over the period 2005–2013 under Hidden Markov Model (HMM) system estimator. And then, the quantitative stock selection strategy based on neural network is studied based on multiple factors of the total market value of the constituent stocks in the SSE 50 Index, the OBV energy wave, the price-earnings ratio, the Bollinger Bands, the KDJ stochastic index, and the RSI indicators. Back testing obtained the conclusion that the Machine Learning strategy is equally valid for Chinese finical market. By analysing the risk of strategic returns, we can also conclude that the Chinese share market is effective in QuantitativeTrading.
