Forecaster is a web-based platform for time-series forecasting. It streamlines training, evaluating, and comparing forecasting approaches, for users without deep technical expertise.
Part of the Kentucky Open Science platform: it runs over the Cresco mesh, with versioned storage for datasets, models, and code in GaiaKeep. See the full stack.
Request access through the information request form.
A. D. Mullen, D. R. Harris, P. Rock, K. Thompson, S. Slavova, J. Talbert, V. K. C. Bumgardner. Implementation and Assessment of Machine Learning Models for Forecasting Suspected Opioid Overdoses in Emergency Medical Services Data. AMIA Annual Symposium Proceedings, 2024, pp. 909-918.
Bridging the Clinical Expertise Gap. arXiv