TIME SERIES BASED PATTERN PREDICTION USING FBPROPHET ALGORITHM FOR COVID-19

Abstract

The beginning of 2020 marked the outbreak of the new pandemic all over the world commonly known as ―COVID-19‖ and since then the number of infected cases all around are increasing rapidly, especially in India. India once becomes the 2nd most infected country and government is having a hard time in patterning and forecasting the spread of COVID-19. The main objective of this paper is to find the regions of spread of coronavirus across different parts of India and analyse the growth rates across the country. This analysis will help to minimize the virus spread, check how well the mitigations are working, how many cases have been prevented. This paper aims at drawing the better statistical model with deep study of number of reported cases with the implementation of Exploratory Data Analysis (EDA) on the basis of several trends from March 2020 to May 2021.For data prediction Prophet time series forecasting agorithm is used to since it handle both logistic growth and peicewise linearity of data.Our analysis can help in understanding various trends of the corona outbreak.