EPIDEMIC MODELING USING MACHINE LEARNING: COVID-19

Author/Creator

Author/Creator ORCID

Department

Computer Science and Electrical Engineering

Program

Computer Science

Citation of Original Publication

Rights

Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan through a local library, pending author/copyright holder's permission.
This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu

Subjects

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.