This AI Accelerator demonstrates how to reconcile (e.g., post-processing to sum appropriately) independent time series forecasts with a hierarchical structure. Reconciling, also known as making "coherent" forecasts, is often a requirement when submitting hierarchical forecasts to stakeholders. This notebook leverages the increasingly popular HierarchicalForecast python library to do the reconciliation on forecasts generated from DataRobot time series deployments. 

Version history
Last update:
‎01-19-2024 12:38 AM
Updated by: