Abstract
To understand the spread of COVID-19, the data sets from Google and GitHub are obtained by using Python and R, and ARIMA model is established for prediction. By visualising the data sets, it can be found that the total trend of the COVID-19 is bimodal and reaches its peaks during the winter and spring time in 2022 and 2023, and this may due to the virus activity and government management. When taking into prediction, ARIMA (3,1,3) is the best predict model to forecast the overall spread trend of COVID-19 as the data is not normal distributed since it keeps fluctuating in the P-P plot, and it can be considered as time series, showing a seasonal pattern. This conclusion is drawn by calculating the values of AIC and BIC to see which model has smallest. At the same time, the ACF and PACF index could determine the p and q value in the model. The model can help to predict the spread of similar diseases.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
