Comparative analysis of volatility forecasting for healthcare stock indices amid public health crises: a study based on the Bayes-CNN model.

In recent years, public health events have significantly impacted various aspects of human production and daily life, particularly in the domains of disease transmission and economic stability. While many scholars have primarily focused on the influence of public health events from the perspective of disease prevention and control, research examining their economic implications, especially regarding public health indices in the securities market, remains relatively scarce. Such studies are crucial for ensuring public health safety and stability. This paper employs the Bayesian Convolutional Neural Network (Bayes-CNN) model to predict financial market volatility influenced by public health events and conducts a comparative analysis. To validate the feasibility of this method, the model is used to analyze the impact of the COVID-19 pandemic on the CSI (China Securities Index) Medical Service Index. The results indicate significant differences in the volatility of the CSI Medical Service Index before and after the outbreak, particularly during the pandemic period. This study also enhances the validity and reliability of its conclusions by incorporating European data and employing the GARCH model. Relevant institutions and individual investors should adopt different regulatory and investment strategies based on the specifics of various public health events to prevent the outbreak of systemic financial risks that could affect social stability. This paper offers a new perspective and methodology for predicting financial market volatility under the influence of public health events, providing valuable insights for investors and decision-makers to better understand and respond to the potential impacts of such events on financial markets.