Statistical machine learning forecasting simulation for discipline prediction and cost estimation of COVID-19 pandemic

Ghosh, Papri; Dutta, Ritam

This paper reports an analysis of statistical machine learning for discipline prediction and cost estimation of the COVID-19 pandemic using correlation regression methodology. Assessing the deadliest pandemic situation across the globe, our simulation-based estimation work mainly targets the exponential rise in the essential requirements for antivaccine that can be served on an emergency basis worldwide. Several medicine companies are trying to find out the anti-COVID vaccine, though the governments of different countries have already taken up the decision of lockdown as a preventive measure to break the chain of COVID-19 outbreak. The demand forecasting of the medicine is now the major issue of the supply chain. This paper proposes a mathematical model by using the machine learning forecasting simulation that studies the existing situation reports based on COVID-19 outbreak issued by the World Health Organization. Furthermore, it has been analyzed the number of existing COVID-19 patients based on the popularity density of the top 15 countries, India and its subcontinental countries that may further help many governments to oversee the upcoming situation of novel coronavirus pandemic.