Analysis and Forecasting of COVID-19 Cases Across Hotspot States of India

This paper attempts to develop a model to predict Novel Coronavirus affected cases in India. The virus is officially named as SARS-CoV-2 and was declared as a pandemic by WHO on 11th March 2020. This pandemic erupted in the Wuhan city of the People's Republic of China in December 2019. By now the whole world is in the grip of this virus. The first case of the COVID-19 in India was reported on 30th January 2020 in the state of Kerala. In India, the Ministry of Health and Family Welfare (MOHFW) keeps the track of COVID-19 cases daily. As of 14th June 2020, the total number of confirmed, recovered, and death cases in India are 332424, 169798 and 9520 respectively. The corresponding world statistics are 7900924, 3769712 and 433065 respectively. The disease is infectious and contagious and is affecting the health of people at large. The government and administration are trying hard to control the disease, and trying to find an effective treatment. This research aims to forecast the number of confirmed cases, recoveries and deaths of India and its six hotspot states (Maharashtra, Delhi, Tamil Nadu, Madhya Pradesh, Rajasthan, and Gujarat). To check the accuracy of the model, the first round of forecast is done from 15/4/2020 to 25/04/2020 based on the data available from 30th January 2020 to 14th April 2020. The second round of forecast is done from 16/05/2020 to 30/06/2020 based on the actual data from 30/01/2020 to 15/05/2020. Auto-Regressive Integrated Moving Average (ARIMA) model has been used to forecast the trend of COVID-19 cases in R programming.