4048854
doi
10.5281/zenodo.4048854
oai:zenodo.org:4048854
user-covid-19
Quentin Chevalier
California Institute of Technology
Geoffrey Magda
California Institute of Technology
Matthew Gonzalgo
California Institute of Technology
Forecasting The Spread of COVID-19 with Enhanced Linear Autoregression
Ethan Mann
California Institute of Technology
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Machine Learning
Autoregression
COVID-19
<p>The COVID-19 pandemic is the focal point of global attention in 2020, as the virus has affected most of the world. Effectively responding to the pandemic continues to be a major and urgent issue; as of September 2020, there is still no widely accepted cure for the disease. To complement medical studies regarding the nature of the virus and provide decision-makers with tools to handle the crisis, Caltech offered the Spring 2020 CS156b course to forecast the probability distribution of the number of COVID-19 related deaths. The challenge was held during April and May 2020, and the predictive goal was to model fatalities as reported by the New York Times (NYT) two weeks into the future on the county level, with predictions evaluated via pinball loss. This paper details our team's model submission, a linear autoregressive model with features for cases and fatalities.</p>
Zenodo
2020-09-24
info:eu-repo/semantics/preprint
4048853
user-covid-19
1.0.0
1601019524.817164
1879060
md5:ec2e54f10f797fbca65b6123eab19e5a
https://zenodo.org/records/4048854/files/covid19_autoregression_model.pdf
public
10.5281/zenodo.4048853
isVersionOf
doi