Covid-19 Pandemic Data Analysis and Forecasting using Machine Learning Algorithms

India reported its first Covid-19 case on 30th Jan 2020 and the number of cases reported heavily escalated from March, 2020. This research paper analyses COVID -19 data initially at a global level and then drills down to the scenario obtained in India. Data is gathered from multiple data sources-several authentic government websites. The need of the hour is to accurately forecast when the numbers will reach at its peak and then diminish. It will be of huge help to public welfare professionals to plan the preventive measures to be taken keeping the economic balance of the country as well. Variables such as gender, geographical location, age etc. have been represented using Python and Data Visualization techniques. Time Series Forecasting techniques including Machine Learning models like Linear Regression, Support Vector Regression, Polynomial Regression and Deep Learning Forecasting Model like LSTM(Long short-term memory) are deployed to study the probable hike in cases and in the near future. A comparative analysis is also done to understand which model fits the best for our data. Data is considered till 30th July, 2020. The results show that a statistical model named sigmoid model is outperforming other models. Also the Sigmoid model is giving an estimate of the day on which we can expect the number of active cases to reach its peak and also when the curve will start to flatten. Strength of Sigmoid model lies in providing a count of date that no other model offers and thus it is the best model to predict Covid cases counts -this is unique feature of analysis in this paper. Certain feature engineering techniques have been used to transfer data into logarithmic scale as is affords better comparison removing any data extremities or outliers. Based on the predictions of the short-term interval, our model can be tuned to forecast long time intervals.