I.J. Intelligent Systems and Applications, 2022, 3, 40-53 Published Online June 2022 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijisa.2022.03.04 Copyright © 2022 MECS I.J. Intelligent Systems and Applications, 2022, 3, 40-53 A Comprehensive Review of Machine Learning Techniques for Predicting the Outbreak of Covid- 19 Cases Arpita Santra 1 , Ambar Dutta 2 1 Amity Institute of Information Technology, Amity University, Kolkata – 700135, India E-mail: arpitasantra988@gmail.com 2 Amity Institute of Information Technology, Amity University, Kolkata – 700135, India E-mail: adutta@kol.amity.edu Received: 29 September 2021; Accepted: 30 March 2022; Published: 08 June 2022 Abstract: At present, the whole world is experiencing a huge disturbance in social, economic, and political levels which may mostly attributed to sudden outbreak of Covid-19. The World Health Organization (WHO) declared it as Public Health crisis and global pandemic. Researchers across the globe have already proposed different outbreak models to impose various control measures fight against the novel corona virus. In order to overcome various challenges for the prediction of Covid-19 outbreaks, different mathematical and statistical approaches have been recommended by the researchers. The approaches used machine learning and deep learning based techniques which are capable of prediction of hidden patterns from large and complex datasets. The purpose of the present paper is to study different machine learning and deep learning based techniques used to identify and predict the pattern and performs some comparative analysis on the techniques. This paper contains a detailed summary of 40 paper based on this issue along with the use of method they applied to obtain the purpose. After the review it has been found that no model is fully capable of predicting it with accuracy. So, a hybrid model with better training should be employed for better result. This paper also studies different performance measures that researchers have used to show the efficiency of their proposed model. Index Terms: Forecasting, Epidemic Covid-19, Machine Learning, Models, Performance Analysis. 1. Introduction Machine learning is a science which promotes the study of computer algorithms such that the system could gain the capability in automatic learning and improve its functionality from past experiences. It aims at the development of computer programs so that it can access data and use it to learn from them. The algorithms are focused on building models from sample data called “training data”. Machine learning algorithms are used in various fields – such as predictive analysis, natural language processing, sentiment analysis and many more. The term machine learning was first used by Arthur Samuel in 1959. Supervised, unsupervised and reinforcement learning are the three broad classification of machine learning algorithms. In supervised learning, the algorithms are trained with labels which means that for a given input the corresponding output is known. In unsupervised learning, no labels are provided to the learning algorithm. The machine itself must find patterns in its input. In reinforcement learning, the algorithms learn from a dynamic environment by using its own mode of solution. It uses trial and error methods and learns from its feedback which it tries to maximize. Some of the applications of machine learning include image and speech recognition, product recommendations, traffic prediction, self-driving cars, spam email and malware filtering, virtual personal assistant etc. Today’s world is full of various types of diseases which may be classified into two categories – infectious and non- infectious. Infectious diseases are caused by microorganisms belonging to different classes. These diseases can spread by various ways- air, water, saliva from infected people and even from other eatables. This may lead to mild to severe fever, cough, cold, and diarrhea and in some severe cases death. Majority of deaths in developing countries are caused due to these infectious diseases which are hard to handle, ones spread. Even today medicines are not there for many diseases. We are living in a country with a population more than 1 billion where adequate healthcare facilities are not available. This makes the situation worse. In order to avoid such deadly situations some mechanisms could be applied which will be capable of predicting such epidemics. Machine Learning has shown the ray of hope in this way. Machine Learning helped scientists and researchers in predicting various epidemics and pandemics along with understanding the pathogen