Prediction mechanisms based on machine learning (ML) have proven their importance in several fields to improve the creation of choices on the long-term course of action. Technological advancements have a quick result in every area of life, be it the medical field or the other field. Many prediction methods are commonly used to handle prediction problems. This study demonstrates the ability of cubic centimeter models to predict the amount of approaching patients with COVID-19 that is currently considered a possible threat to clustering. Specifically, 3 common prediction models, like Extreme Gradient Boosting Machine (XGBM), LIGHT Gradient Boosting Machine (LIGHT GBM) and Random Forest mechanisms are used in this study to predict threatening factors of COVID-19. 3 styles of predictions are created by each of the models, such as the number of new infected cases, the number of deaths, as well as the range of recoveries in the next ten days. The results created by the study prove that it is a promising mechanism to use these means in this COVID-19 pandemic situation.

.