Projects

    There are 7 public projects and 1 project with access limited to collaborators only.

    Project Owner Description Summary
    ECDC European COVID-19 Forecast Hub (No logo) epiforecasts The goal of this repository is to create a standardized set of data on forecasts from experienced teams making projections of incident case and death numbers due to COVID-19 in the EU and the United Kingdom.
    48 models, 1214 forecasts, 232,619 predictions
    COVID-19 Forecasts
    covid19hub The goal of this repository is to create a standardized set of data on forecasts from experienced teams making projections of cumulative and incident deaths due to COVID-19 in the United States.
    106 models, 5043 forecasts, 73.4 million predictions
    Docs Example Project
    cornell A template project for learning how to interact with Zoltar. Typically, a full description of the project would go here. You could include narrative details about what seasons are included, what group has provided data, whether the project focuses on real-time or retrospective forecasts.
    One model, one forecast, 29 predictions
    2020 Election Forecasts
    ydh28 This project stores forecasts from multiple election forecast sites, including FiveThirtyEight and the Economist, for ease of access and comparison.
    Seven models, 945 forecasts, 76,224 predictions
    CDC Real-time Forecasts
    khoa Guidelines and forecasts for a collaborative U.S. influenza forecasting project.
    44 models, 2167 forecasts, 333,713 predictions
    CDC Retrospective Forecasts
    (No owner) Guidelines and forecasts for a collaborative U.S. influenza forecasting project.
    27 models, 5647 forecasts, 869,638 predictions
    Aggregating Statistical Models and Human Judgement
    allicodi This project aims to provide public health officials metaforecasts---a combination of probabilistic predictions from computational models, subject matter experts, and trained forecasters---of the COVID-19 outbreak.

    A consensus forecast is an equally weighted combination of probabilistic predictions from individuals. We included consensus forecasts from individual forecasters on Metaculus (https://www.metaculus.com/questions/) and from Good Judgment Open (https://www.gjopen.com/). A metaforecast is also included: an equally weighted combination of consensus forecasts and of the COVID-19 Forecasthub ensemble.

    Each month individuals contribute forecasts for incident cases, deaths, hospitalizations, and cumulative number of vaccines at the US national level. Additional targets for forecasting depend on public health needs. Individuals can produce forecasts at the beginning of each month until the middle of the month.

    Files are named as YYYYMMDD_YYYYMMDD.csv and corresponds to the year (YYYY), month (MM), and day (DD) forecasting began and the year, month, and day forecasting ended. All forecasting ends at 2PM EST.

    Three models, 0 forecasts, 0 predictions