Curating a COVID-19 Data Repository and Forecasting County-Level Death Counts in the United States

Explore a comprehensive lecture on COVID-19 data curation and forecasting presented by Bin Yu, Chancellor's Distinguished Professor at UC Berkeley. Delve into the process of creating a large-scale COVID-19 data repository and learn about developing accurate short-term predictions for cumulative death counts at the county level in the United States. Discover the Combined Linear and Exponential Predictors (CLEP) ensemble method, which incorporates various forecasting techniques including county-specific, shared, and demographics-based predictors. Understand the application of Maximum Error Prediction Intervals (MEPI) for assessing forecast uncertainty, achieving over 94% coverage rate for two-week predictions. Gain insights into how these forecasts are being utilized by Response4Life to determine medical supply needs for hospitals across the country, directly impacting the distribution of critical resources in the fight against COVID-19.

Curating a COVID-19 data repository and forecasting county-level death counts in the United States