Machine Learning Models and Transfer Models for Measuring Impact of the Pandemic on Communities
| dc.contributor.author | Berdibekov, Timur | |
| dc.date.accessioned | 2022-01-20T00:15:10Z | |
| dc.date.available | 2022-01-20T00:15:10Z | |
| dc.date.issued | 2021-04-28 | |
| dc.description.abstract | This paper studies the relationship between the 2019 Novel Coronavirus (COVID-19) pandemic, its public health and economic impact, and rates of economic inclusion and access to banking services throughout the pandemic in the United States. For select U.S. counties, this paper examined COVID-19 infection and mortality rates, unemployment rates and the number of bank closures, and the rate of economic inclusion to discover any notable relationships. Lastly, select features are evaluated for the predictive capability of the county and county-equivalent rates of unbanked households to better inform policy making given that the unbanked household rates are unknown for most counties. | |
| dc.identifier.uri | https://hdl.handle.net/1920/12225 | |
| dc.rights | Attribution-NonCommercial-NoDerivs 3.0 United States | |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/3.0/us/ | |
| dc.subject | COVID-19 | |
| dc.subject | Machine learning | |
| dc.subject | Artificial intelligence | |
| dc.title | Machine Learning Models and Transfer Models for Measuring Impact of the Pandemic on Communities | |
| dc.type | Working Paper |