Predictive analysis of novel coronavirus using machine learning model - a graph mining approach

Abstract

Graph mining is an important research field and it has received extensive attention. We can process, analyze, and extract meaningful information from a large amount of graph data. There are a large number of applications e.g. Biological network or web data. Machine learning is an example of biological networks algorithm. Machine learning and computational intelligence have promoted the development of predictive systems in a wide range of fields. These recommendations are based on contextual information that is explicitly provided or widely collected. Predictive systems usually improve solutions and increase task efficiency. Real-time data/information is not only a popular predictive system but also an abstraction of many real-world applications designed to increase resources and reduce risks. We can learn to use predictive analytics to predict the positive outcomes of these risks. These predictive analytics can look at the risks of past successes and failures. This paper attempts to develop an accurate (i.e. real-time) prediction recommendation system to predict new estimates of positive cases of coronavirus. Graph mining tool (i.e. machine learning) applied on the Indian dataset to predict the number of positive cases in daily, weekly, and monthly cases.