A Comparative Study of Arima and Sarima Models to Forecast Lockdowns Due to Covid-19

Abstract

Abstract The aim of this paper is to create a machine learning model that can forecast and alert users about the COVID−19 illness lockdown period. World Health Organization (WHO) data on novel coronavirus were the subject of exploratory data analysis, which used a variety of techniques to identify the proper parameters for the data so that the Auto-regressive Integrated Moving Average (ARIMA) and Seasonal Auto-regressive Integrated Moving Average (SARIMA) models could be trained on it. Using data from January 2020 to May 2022 during the previous two years, the machine learning model is trained. In APPENDIX G the findings for the ARIMA(5,1,5)(0,0,0)(0) and SARIMA(5,1,5)(0,0,0)(9) models are compared. The dependant variable for the Automatic ARIMA and SARIMA functions might be either new cases or death cases. The current model having these parameters can be used to work on the data of diseases that have a tendency to spread widely and quickly. This study can be extremely helpful in predicting lockdown times so that different government entities can make preparations in accordance.