Paper Title
Machine Learning Approaches for the Prediction of Covid-19 Pandemic

Abstract
Corona virus (covid-19) is an infectious disease caused by SARS-CoV-2 virus. It has been revealed as a global pandemic that causes danger to human lives and needs due attention and instant diagnosis. Since the first known infection discovery in December 2019 up to 13 January 2023, the number of covid-19 patient cases and deaths has exceeded 670.2 million and 6.7 million, respectively. People with covid-19 have had symptoms ranging from fever to breathing difficulty and loss of speech or mobility. Many countries have encountered limitations in their test capacity, access to testing kits, hospital beds, hospital equipment and healthcare personnel. These limitations have created difficulties on timely treatment, identification, and care of covid-19 patients. Utilizing machine learningbased prediction approaches could contribute a lot in supporting the decision-making tasks for instantly deciding the presence of covid-19. ML algorithms have been widely used in several fields of health and medicine. Thus, in this paper, we develop the ML models for covid-19 pandemic prediction through applying four ML algorithms – the Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boost (XGBoost) and Artificial Neural Network (ANN). For experimentation, we employed R programming language and the covid-19 symptoms and presence dataset. Our ANN based model has demonstrated its efficiency in covid-19 pandemic prediction and achieved the best performance in terms of all the metrics as compared to RF, SVM and XGBoost based models. For instance, it outweighs these models by attaining 98.6% accuracy. Keywords - Machine Learning Algorithms, Covid-19 Prediction Models, Random Forest (RF), Support Vector Machine (SVM), Xgboost, Artificial Neural Network (ANN).