Application Of Improved GARCH Model

In recent years,many scholars have continued to study time series data,and many more mature theories have also appeared,such as parameter estimation and prediction.Aiming at the strong influence points,the local influence analysis method has become an identification method.However,the identification of abnormal points and strong influence points in the time series model can be complicated due to a certain relationship in the data points of the model.This study firstly improved the Generalized Autoregressive Conditional Heteroskedast model for the issue that sales data have singular information when making use of the model,and applies the improved outlier detection method to detect abnormal points,and then we use the step-by-step local influence method to detect the strong influence points,which were processed by the iterative method.Secondly,in order to describe the peak and fat tail of the financial time series,as well as the leverage effect,this work used the skewed-t Asymmetric Power Autoregressive Conditional Heteroskedasticity model based on the Autoregressive Integrated Moving Average Model to analyze the two sets of sales data after processing.Empirical analysis showed that the model considering strong influence points has better prediction effect than the model only considering outliers.In this way,it can help the decision-making layer of the enterprise to have a certain grasp of the trend of goods sales,so that resources can be effectively integrated,rationally planned,and their competitiveness can be improved among peers.