ABSTRACT
The World Health Organization confirmed coronavirus as global pandemic on March 11, 2020. The first wave started during March–April 2020, followed by second wave during September–November 2020 and third wave during January–February 2021 in many parts of the world. In spite of vaccinations and herd immunity, the new mutating virus is continuously inducing new spikes and asymptotic death rates in several countries. Various prediction models are used to predict the outcomes of pandemic. Machine learning regression models such as Least Absolute Shrinkage and Selection Operator (Lasso), Linear Regression, Ridge, Elastic-Net, Random Forest, Adaptive Boosting (AdaBoost), Light Gradient Boosted Machine (LGBM), and Extreme Gradient Boosting (XGBoost) are considered to predict and study the exponential increase of mortality rate, number of confirmed cases, and recovery rate. Also, Facebook Prophet Model is used to predict the outbreak of COVID-19. To build these models, COVID-19 real-time dataset is extracted from Johns Hopkins University that considers the number of confirmed cases, total deaths, and number of recovered cases. Information such as country/region, confirmed cases, province/state, recovered cases, death rate, and last update is considered to make predictions. These models were trained, tested, and compared for their performances based on the parameters R-squared value, R-squared modified score, Mean Squared deviation and Root Mean Square Error. The results are tabulated to observe the best model for pandemic outbreak prediction. Based on the results of these models, the concerned officials can infer the necessary measure that has to be taken to control the outbreak of COVID-19 pandemic. © 2022 Elsevier Inc. All rights reserved.