Abstract Corona Virus unwellness 2019 (COVID-19) could be an illness caused by Severe Acute metabolism Syndrome Corona Virus 2 (SARS-CoV-2) and was initial diagnosed in China in Dec, 2019. Dr. Tedros Adhanom Ghebreyesus, World Health Organization (WHO) director-general on March eleventh declared the COVID-19 pandemic. Machine learning (ML) based mostly prediction mechanisms have established their significance to anticipate in perioperative outcomes to boost the choice creating on the long run course of actions. The ml models have long been utilized in several application domains that required the identification and prioritization of adverse factors for a threat. many predictions strategies square measure being popularly wont to handle prediction issues. This study demonstrates the potential of ml models to forecast the quantity of coming patients suffering from COVID-19 that is presently thought of as a possible threat to human beings.
In specific, normal prediction models, like linear regression (LR), least absolute shrinkage and choice operator (LASSO), support vector machine (SVM), and exponential smoothing (ES) are utilized in this study to forecast the threatening factors of COVID-19.
The results prove that the es performs best among all the used models followed by LR and LASSO that performs well in prediction the new confirmed cases, death rate similarly as recovery rate, whereas SVM performs poorly all told the prediction situations given the offered dataset.

Keywords: machine learning , covid 19, LR,LASSO

| DOI: 10.17148/IARJSET.2021.8462