Open AccessCOVID-19 Future Predictions Using 4 Supervised Machine Learning Models
Author(s) -
Aditi Vadhavkar,
Pratiksha Thombare,
Priyanka Bhalerao,
Utkarsha Auti
Publication year - 2022
Publication title -
international journal of advanced research in science, communication and technology
Language(s) - English
Resource type - Journals
ISSN - 2581-9429
DOI - 10.48175/ijarsct-2235
Subject(s) - lasso (programming language) , machine learning , support vector machine , artificial intelligence , computer science , exponential smoothing , covid-19 , prioritization , identification (biology) , engineering , medicine , management science , botany , disease , pathology , world wide web , infectious disease (medical specialty) , computer vision , biology
Forecasting Mechanisms like Machine Learning (ML) models having been proving their significance to anticipate perioperative outcomes in the domain of decision making on the future course of actions. Many application domains have witnessed the use of ML models for identification and prioritization of adverse factors for a threat. The spread of COVID-19 has proven to be a great threat to a mankind announcing it a worldwide pandemic throughout. Many assets throughout the world has faced enormous infectivity and contagiousness of this illness. To look at the figure of undermining components of COVID-19 we’ve specifically used four Machine Learning Models Linear Regression (LR), Least shrinkage and determination administrator (LASSO), Support vector machine (SVM) and Exponential smoothing (ES). The results depict that the ES performs best among the four models employed in this study, followed by LR and LASSO which performs well in forecasting the newly confirmed cases, death rates yet recovery rates, but SVM performs poorly all told the prediction scenarios given the available dataset.