EPIDEMIC MODELING USING MACHINE LEARNING: COVID-19

Abstract

This research seeks to determine if population density effects the morbidity or infection rate of COVID-19 in a given region. It is driven by the research question: What underlying conditions make a country or region more vulnerable to COVID-19? I hypothesize that, population density significantly impacts the rate of COVID-19 cases and deaths for a given region. As such, population density is a key feature for training a predictive model. To test this hypotheses, I trained a series of predictive models. Each model is trained on 28 days of data and forecasts 14 days. Models are trained with and without population density. I evaluated all models using Mean Absolute Error, Root Square Mean Error, and R2. These metrics provide a means to evaluate and compare the performance of the models. The results indicate that a correlation exists between population density and the rate of COVID-19 cases and deaths for a given region. Additionally, it demonstrates the utility of using population density as a feature.