Author(s)

Muhan Zhu

Corresponding Author

Muhan Zhu

ABSTRACT

This paper uses propensity matching score method and double difference model to measure the impact of this event on stock information content by means of the natural experimental platform of A-shares incorporating MSCI index. By comparing the excess returns of matching stocks and underlying stocks before and after the announcement day, it is found that compared with the underlying stocks, the excess returns of matching stocks are not significant, and the market reaction is not obvious. Moreover, the excess return of the underlying stocks that cannot be matched by propensity score matching method is lower than that of the matching stocks, which is similar to the results of Ni et al. (2020), and supports the inclusion of the underlying index events. It is through the information-driven channel rather than the demand-driven channel that leads to excess return. Next, in order to verify this hypothesis, this paper uses the difference-in-difference model to explore the impact of MSCI index on stock information quality by using sample stocks (underlying stocks and control stocks) from May 2016 to May 2019. The results show that the event significantly improves the information content of stocks and reduces the synchronization between stocks and markets, that is, the information-driven hypothesis wins. Load forecasting is very important for power dispatching. Accurate load forecasting is of great significance for saving energy, reducing generating cost and improving social and economic benefits. In order to accurately predict the power load, based on BP neural network theory, combined with the advantages of Clementine in dealing with big data and preventing overfitting, a neural network prediction model for large data is constructed.

KEYWORDS

MSCI, PSM-DID