Glossary
What is N-BEATS? Definition and meaning
A fully connected architecture of stacked blocks that decompose a series into trend and seasonality.
Definition
N-BEATS: A fully connected architecture of stacked blocks that decompose a series into trend and seasonality.
In short: Deep neural basis expansion for forecasting.
When it is used
Accurate univariate forecasting without feature engineering.
Learn more
The full guide to N-BEATS explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: Multimodal models · Next term: n8n