Infecting billions of people and death of over 6.5 millions people and loss of economy across the world, this COVID-19 outbreak caused by SARS-COV-2 has uncover the poor health management in the large populated country like India. Therefore, there is a requirement of detailed study i.e. Systematic Literature Review(SLR) of existing models by analysing the predicting behaviour of epidemic which plays a vital role in controlling the spread in future. Our study considered prediction models of COVID-19 which includes case study of India using machine learning and deep learning. This study includes only scholarly peer-review research articles of two renowned databases, Web of Science and Scopus from 2020–2022. PRISMA(Preferred Reporting Items for Systematic Reviews and Meta Analysis) guidelines have used for results and discussion. Before screening 317 articles were reported and after screening, eligibility of inclusion/exclusion criteria, 51 research articles were included for the final study. This SLR examined articles thoroughly, identified different machine learning, deep learning prediction models, identified research gaps/limitations, future scopes, and examined different performance metrics used in these studies. An additional objective of this research is to identify limitations and future directions provided by each research article which were not covered in any SLR on COVID-19.