Ensemble forecasting with IBM Granite time-series models

Thu, Oct 22 · 7:51 AM UTC 2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

★ Tier-1 Source

Four Granite forecasting models feed a common quantile interface and one of two aggregation methods.

Four open Granite models, one extensible forecasting interface, and less guesswork about which model to use.

Key facts

The Probabilistic Ensemble achieves the lowest MASE among these six forecasts: 0.683 compared with 0.685 for PatchTST-FM-r2
For example, the 0.1 and 0.9 quantiles define a central forecast interval with nominal 80% coverage
In the 20 October 2026 comparison, the ensemble approach ranks 3rd among eligible systems on MASE Rank and CRPS Rank
Figure: GIFT-Eval average-rank standings on 20 October 2026, showing both Granite ensembles alongside the ten best eligible reference systems per metric

Summary

Pre-trained time-series models can forecast without training on your dataset, but you still have to choose one. Granite Timeseries Ensemble reduces that choice to a sensible default. The idea will be familiar from weather forecasting. Install Granite TSFM and load the recommended four-model recipe directly from .

Read full article at Hugging Face →

#U.S.