Covid-19 Future Forecasting using Machine Learning and Deep Learning Models

Forecasting mechanism used by Machine learning (ML) and deep learning model have proved their significance to predicting the in operative outcomes to enhance the choice making on the longer term course of actions. The ML models and deep learning models have long been utilized in many application domains which needed the identification and prioritization of adverse factors for a threat. Several prediction methods are being popularly wont to handle forecasting problems. This study demonstrates the potential of ML and Deep Learning models to forecast the amount of upcoming patients suffering from COVID-19 which is presently considered as a possible threat to mankind. In particular, three standard forecasting models polynomial regression (PR), Autoregressive Integrated moving average model (ARIMA), and CNN based Long Short-Term Memory networks(CNN -LSTM) have been used in this study to forecast the threatening factors of COVID-19. Two types of predictions are made by each of the models, such as the number of newly infected cases, the number of deaths in the next 10 days. The result gained by this study proves that these methods work best for the current scenario of the covid-19 pandemic. IndexTerms—COVID-19, polynomial regression, ARIMA, CNN-LSTM.