Real-time forecasts and risk assessment of novel coronavirus (COVID-19) cases: A data-driven analysis

Tanujit Chakraborty; Indrajit Ghosh

In December 2019, Wuhan city of China became the centre of an outbreak of pneumonia of unknown cause, latter named as coronavirus disease 2019 (COVID- 19) , which raised intense attention not only within China but internationally [13; 32] . The COVID-19 pandemic is the most significant global crisis since the World War-II that affected almost all the Countries of our planet [4] . As of April 4, 2020, an outbreak of COVID-19 has resulted in 11, 16, 643 confirmed cases with reported deaths of 59,170 worldwide [22] . On March 11, WHO publicly characterized COVID-19 as a "global pandemic", and shortly after that, the United States declared COVID-19 outbreaks a national emergency. The COVID-19 has caused a great threat to the health and safety of people all over the world due to its widespread and potential harm. Thus, the studies of the novel COVID-19 epidemics and its future development trend has become a cutting-edge research topic at this moment. We are therefore motivated to ask: (a) Can we generate real-time forecasts of daily new COVID-19 cases for countries like Canada, France, India, South Korea, and the UK? (b) What are the probable causal variables that have significant impacts on the case fatality rates for the profoundly affected countries?