Group 1 - The core viewpoint of the article emphasizes the necessity for securities firms to enhance market risk measurement models to better identify, warn, expose, and manage financial risks in a complex market environment [1] - Value at Risk (VaR) has become a key indicator for quantitative analysis of market risk since its introduction by JP Morgan in 1994, gaining recognition from regulatory bodies like the Basel Committee [1] Group 2 - Traditional VaR measurement methods such as historical simulation, parametric methods, and Monte Carlo simulation have limitations, particularly in capturing tail risks and the dynamic nature of volatility [2] - GARCH models, which account for volatility clustering and the heavy-tailed characteristics of financial data, are better suited for modeling the dynamic changes in volatility [2][4] Group 3 - Empirical analysis using the CSI 300 index from 2014 to 2016 demonstrates that GARCH models outperform traditional VaR methods during periods of high market volatility, effectively capturing the clustering of volatility and the leverage effect [5][14] - The GARCH(1,1) and EGARCH(1,1,1) models were selected for their ability to fit extreme values and reflect market dynamics accurately, with a confidence level set at 95% [12] Group 4 - The findings indicate that during periods of significant market fluctuations, GARCH models can quickly adjust VaR values to reflect potential risks more accurately, making them essential tools for financial institutions in risk management [14][15] - The research highlights the importance of dynamic risk-related models in preventing systemic financial risks and fulfilling the early identification and management requirements of financial risks [15]