Economic Inclusion in the United States: Predictive Analysis of COVID-19 pandemic on County Rates of Unbanked Households

摘要

COVID-19 pandemic has a significant effect on the unemployment rate in the United States. However, the economic effect in different states is not the same for each household. In this work, Our goal is to capture and outline the relationships between pandemic incidence, economic inclusion, unemployment, and bank branch closures in order to understand the emerging relationship between the coronavirus pandemic, rates of economic inclusion, and economic well-being of localities. Furthermore, we machine learning algorithms to evaluate the predictive power of coronavirus incidence and fatality rates, county-level unemployment, and bank branch closure rates on rates of economic inclusion. Also, a natural language processing approach is used to analyze the unemployment COVID-19 textual data. We use BERT as a powerful transformer for sentiment classification on COVID-19 unemployment data.