Welcome to the Zoltar forecast archive, a website developed by the Reich Lab in the Department of Biostatistics and Epidemiology at the University of Massachusetts Amherst.
Designed to improve the robustness of forecasting research, Zoltar is a research data repository that stores forecasts made by external models in standard formats and provides tools for validation, visualization, and scoring. It builds off of a foundation of core ideas and data structures first introduced in 2019 by predx. Zoltar can host real-time or retrospective forecasting challenges, competitions, or research projects, with users specifying the forecast targets.
In June 2020, we released a preprint describing the concepts, data model, and intended scope of Zoltar.
Please visit the Zoltar Documentation Site for more information, along with guides for users, researchers, and developers. We have an API that supports programmatic push and pull access to forecast data, including forecasts themselves, model metadata, and forecast scores. We have also developed zoltr, an R package, and zoltpy, a Python library, to facilitate accessing the Zoltar API and the underlying forecast data.
This work has been supported by a grant from the National Institutes of General Medical Sciences (R35GM119582) and is a part of the MIDAS Network. The content is solely the responsibility of the authors and does not necessarily represent the official views of NIGMS, or the National Institutes of Health.
If you have questions about this site, please contact us at email@example.com. For account requests, please fill out the Zoltardata.com user request form to be added to our beta-tester invitation queue.