Forecasting The Prevalence Of COVID-19 Outbreak In India Using Seasonal Autoregressive Integrated Moving Average Model

  • P. Manigandan, K. Alagirisamy, D. Pachiyappan, K. Lokesh

Abstract

Objectives

The novel epidemic of the coronavirus (COVID-19) becomes a global threat. Till 30 April 2020, 1,801 coronavirus cases were infected in India including 75 deaths case which interprets how worst the epidemics have affected India. The purpose of the study is to find the best predictive models for daily Infected, recovered, and death cases in India. To examine the Confirmed, recovered and death case of the Corona Virus, we aim to compare the study to report the prediction of the coronavirus in India.

Methods

The novel epidemic of COVID-19 patient dataset has extracted from the India World health origination (WHO) website includes Infected, recovered and death cases from mid-March to end-April were used to establish. Estimate the Seasonal ARIMA model to forecasting the prevalence of COVID-19 over the subsequent 30 days.

Result

The Seasonal ARIMA model with the lowest RMSE (root mean squared error), MASE, and MAE mean absolute error was finally model selected for in sample simulation. The prediction of COVID-19 patients could obtain the value of recover cases of 1347, which could be an infected value of 2959 and death cases of 162 at the end of May.

Conclusion

This study suggested that the most accurate prediction of COVID-19 prevalence in India using the Seasonal ARIMA model was proposed as a useful tool for monitoring epidemics.

Published
2020-06-06
How to Cite
P. Manigandan, K. Alagirisamy, D. Pachiyappan, K. Lokesh. (2020). Forecasting The Prevalence Of COVID-19 Outbreak In India Using Seasonal Autoregressive Integrated Moving Average Model. International Journal of Advanced Science and Technology, 29(04), 9288 -. Retrieved from http://sersc.org/journals/index.php/IJAST/article/view/30713