Covid-19 Future Forecasting using Supervised Machine Learning

Machine learning (M-L) based forecasting techniques have demonstrated their value in predicting perioperative outcomes in order to improve decision-making about the future course of action.The identification and ranking of negative aspects for a threat was a long-standing need in many application areas where ML models were deployed.Many prediction techniques are now in use to address forecasting issues.This work shows how machine learning (M-L) models can be used to forecast the amount of COVID-19 patients who will be affected in the future, which is currently believed to be a threat to humanity.In this work, the threatening elements of COVID-19 were anticipated using four common forecasting models, Data collection,Construction of networks, Analysis of spreader nodes and Analysisof results.Each model predicts one of three things: the number of newly infected cases, the number of fatalities, and the number of recoveries over the course of the next daysThe study’s Findings indicate that there is a possible benefit to using these methods in the current COVID-19 pandemic scenario strategy.The findings show that the outperforms Construction of networks is the best in forecasting new confirmed cases, mortality rates, and recovery rates, followed by Analysis of spreader nodes and Analysis of results, while does badly in all situations where predictions are made using the dataset that is currently available.