The study analyzed the volatility of the CSI 300 stock index from 2016 to 2021. They found that the index's returns have specific statistical characteristics like peaks, thick tails, and asymmetry. An ARMA (2,3) model effectively predicted future trends. The model showed a cluster effect and conditional heteroscedasticity, which was better captured by a GARCH (1,1) model. The GARCH model indicated that market risk is significant and has a lasting impact on future forecasts.