Empirical analysis of corporate innovation, investor focus and stock slumps risk based on fuzzy mathematics and function optimization

Support vector machine need to choose kernel function according to data distribution characteristics, while iterative algorithm of function parameter optimization can effectively improve the validity of data analysis. Using a sample of A-share listed firms in China from 2007-2017, this paper discusses the impact of corporate innovation on stock price crash risk and the moderating effect of investors' attention on the relationship between the two under the triple effect of enhancing confidence, interpreting information and releasing panic. The results show that: (1) the innovation output is negatively correlated with the stock price crash risk, and the inhibition of substantive innovation is more significant than that of strategic innovation; Investors' focus mainly has the effect of enhancing investor confidence, thus strengthening the negative correlation between the two. (2) R&D is positively correlated with the stock price crash risk. Investors' focus helps to alleviate the information asymmetry and play the effect of information interpretation, thus weakening the positive correlation between the two; (3) the capitalization of development expenses in R&D has not really promoted the enterprise value but has become a means for insider to reduce their holdings and cash. The stock price crash risk is aggravated by the widespread sell-off caused by panic reaction of investors. The research in this paper has certain theoretical and practical significance to improve the substantial innovation of corporates, restrain insider trading behavior, protect the interests of investors and then maintain the stable development of capital market.