COVID-19, the disease caused by a novel Severe Acute Respiratory Syndrome Corona Virus-2 (SARS-CoV-2), is a highly contagious disease. On January 30, 2020 the World Health Organization (WHO) declared the outbreak as a Public Health Emergency of International Concern. As of September 10, 2020; 27891329 laboratory-confirmed and 903991 deaths have been reported globally. Time series models play an important role in predicting the impact of the COVID-19 outbreak and taking the necessary measures to respond to this crisis. In this work, Autoregressive Integrated Moving Average (ARIMA) model is employed to forecast the epidemiological trend of COVID-19 prevalence of US, India and Brazil, the most affected countries as of September 10, 2020. The prevalence data of COVID-19 from 31 December 2019 to 10 September 2020 were collected from the WHO website. Different ARIMA models were formed with different ARIMA parameters. ARIMA (1,2,1), ARIMA(2,2,0) and ARIMA(2,2,2) were considered as the best model for forecasting the confirmed cases of US, India and Brazil whereas ARIMA(1,1,1), ARIMA(0,2,1) and ARIMA(2,2,3) were considered as the best model for forecasting the number of death cases in these countries in the next four weeks. Forecasting COVID-19 prevalence trend of US, India and Brazil can help health authorities and politics to plan and supply resources effectively as well as make a plan to maintain the stable national economic growth in this terrible situation. It also helpful to the Government and public to take necessary precautions as early as possible.

F Ramesh Dhanaseelan1, A Oliver Bright2, M. Jeya Sutha3, M J Brigit Gilda4
St. Xavier’s Catholic College of Engineering, India1,2,3, M.S. University Constituent College of Arts and Science, India4

ARIMA, Time Series, Forecasting, COVID-19, Pandemic
Yearly Full Views
Published By :
Published In :
ICTACT Journal on Management Studies
( Volume: 6 , Issue: 4 , Pages: 1304-1310 )
Date of Publication :
November 2020
Page Views :
Full Text Views :

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.