Research On Market Sentiment Quantitative Timing From China GEM

Quantitative investment has gone through half a century of development in foreign countries. It has formed a relatively complete theoretical system and has made great achievements. For example, the quantitative investment master from United States, James Simons, whose Medallion Fund has made brilliant achievements. The Fund from established in the period 1998 to 2008, the composite rate of return reaches 36%. And the fund performance exceeds in value over the management of investment known Soros Quantum Fund. Due to the short history of the capital market, our country current research on the theory of quantification is still relatively small. In addition, traditional financial theory is based on a rational and efficient market hypothesis (EMH) as the theoretical basis, but as the many market anomalies appear, the traditional financial theory has been unable to explain these problems. So the behavioral finance quietly rises in the eighties of last century. Behavioral finance believes that the essence of all market behavior is human behavior, and investors often affected by their own emotions. Therefore, investor sentiment will affect market in the end. In summary, the focus of this study is a how to construct the investment strategy which can combine the market sentiment and quantitative investment.Based on existing literature and data research related to the GEM market, this study attempts to build the investment strategy of market sentiment quantitative timing from China GEM. First, regarding to the part of building market sentiment index, we build the market sentiment index using principal component analysis. Secondly, regarding to the part of build quantitative timing strategy. First of all, the study analyze the relationship between market sentiment index and the GEM index using vector auto regression model (VAR). Then we analyze the characteristics of the market sentiment volatility using EG ARCH (1,1) model. In the end, we build the quantization timing strategy based on the above findings. Finally, we analyse the effectiveness of the quantitative timing strategy, using python programming language and as the GEM index funds for the study object.