conformal prediction

Uncertainty Quantification with Conformal Prediction in Energy Data

Tarek AlSkaif, Associate Professor, Energy Informatics, Wageningen University (WUR)

Feb 1, 12:00 - 13:00

B9 L2 R2325

conformal prediction machine learning uncertainty quantification

The talk will introduce the fundamentals of conformal prediction (CP) - a flexible, model-agnostic uncertainty quantification framework for generating statistically valid uncertainty estimates in energy applications - and demonstrate how it can be layered on top of machine learning models to produce reliable prediction intervals.