PEAK: Policy Event Assessment of COVID-19 Cases at the Start of the Pandemic in New York City

The impact of events and associated public health announcements on COVID-19 incidence remains an interesting and open question for future response and prevention. To address this issue, we propose a policy event impact assessment framework (PEAK) that quantifies the impact of policies and events on COVID-19 incidence in this paper. PEAK uses time-series change point detection to estimate how health policies and events affected COVID-19 incidence during the most difficult period of the pandemic experienced in New York City and uses the long short-term memory for impact analysis at each change point. We analyze 26 public announcements on COVID-19 and events that occurred in New York City from March 2020 to February 2021. The results show the top 10 largest-impact change points identified by PEAK and the events that caused such impacts.