Scalable Predictive Time-Series Analysis of COVID-19: Cases and Fatalities
This work provides predictive analysis for public health planning during the COVID-19 pandemic, but it is incremental as it applies existing methods to new data.
The paper forecasts COVID-19 cases and fatalities in Los Angeles and New York using time-series models like ARIMA, ETS, and Facebook Prophet, and classification models to show weather does not affect cases, with models run on legacy and big data platforms and accuracy presented.
COVID 19 is an acute disease that started spreading throughout the world, beginning in December 2019. It has spread worldwide and has affected more than 7 million people, and 200 thousand people have died due to this infection as of Oct 2020. In this paper, we have forecasted the number of deaths and the confirmed cases in Los Angeles and New York of the United States using the traditional and Big Data platforms based on the Times Series: ARIMA and ETS. We also implemented a more sophisticated time-series forecast model using Facebook Prophet API. Furthermore, we developed the classification models: Logistic Regression and Random Forest regression to show that the Weather does not affect the number of the confirmed cases. The models are built and run in legacy systems (Azure ML Studio) and Big Data systems (Oracle Cloud and Databricks). Besides, we present the accuracy of the models.