Applying Regressive Machine Learning Techniques in Determination of COVID-19 Vaccinated Patients’ Influence on the Number of Confirmed and Deceased Patients

Vaccinations are one of the most important steps in combat against viral diseases such as COVID-19. Determining influence number vaccinated patients on infected population represents a complex problem. For this reason, aim research is to model total or fully and deceased patients. Five separate modeling algorithms used: Linear Regression (LR), Logistic (LogR), Least Absolute Shrinkage Selection Operator (LASSO), Multilayer Perceptron (MLP), Support Vector (SVR). Cross-correlation analysis performed determine optimal lags data assist obtaining better scores. The cross-validation models performed, evaluated using Mean Percentage Error (MAPE). for four different countries: Germany, India, United Kingdom (UK), States America (USA). Models with an error below 1% found all modeled cases, best being achieved either by LR MLP methods. obtained results indicate that vaccination rates confirmed exists can be ML methods relatively high precision.