Built-in statistical forecasting — exponential smoothing in the forecast wizard

Started by Marcus Delacroix · 1 year, 1 month ago · 2 replies · 1 view
Marcus Delacroix Participant
1 year, 1 month ago

It would be great if Fabric Plan had a built-in statistical forecasting option (exponential smoothing, trend line extension) that works directly on semantic model measures without requiring an external Fabric Notebook.

2 Replies
Head of Financial Planning & Analysis · Nexa Retail Group · 1 year, 4 months ago

For retail, a seasonal decomposition + trend initialisation would be the killer feature. The current workaround via Fabric Notebooks works but requires Python skills that most FP&A teams don't have.

Analytics Practice Lead · Vantage Analytics India · 1 year, 4 months ago

This would lower the barrier significantly for finance teams who want statistical baselines but don't have data scientists. Even a simple linear trend or exponential smoothing option in the forecast initialisation wizard would cover 80% of use cases.

Viewing 2 replies - 1 through 2 (of 2 total)

Enterprise planning, Integrated with PowerTable and Intelligence, native to Microsoft Fabric. Co Engineered with Lumel.
BUILT ON