Skip to main content

Build a forecast

Your data needs gold published for Forecast, status ready, 30+ rows, and a datetime column. The sample is AirPassengers.

Open the wizard​

  1. Sidebar → Data Intelligence → Forecast (/forecast).
  2. Click New Forecast.

Train from gold​

  1. Data source → select gold artifact (Forecast-enabled, status ready).
  2. Forecast interval: Hourly, Daily, Weekly, Monthly, or Quarterly. Match how the series was collected. A monthly series trained as hourly will not track the data.
  3. Analysis step: review seasonality, trend, algorithm hint.
  4. Name the forecast → Train.
  5. Open from list when training completes.

Train from sample​

  1. Data source → Sample dataset → AirPassengers.
  2. Set Interval → Monthly → Train.

After training​

  1. Forecast detail page → Deploy → Generate API key.
  2. Monitor on asset page and Usage.

Next steps​

Troubleshooting​

Analysis: invalid data. Republish gold with a datetime column and numeric values.

No gold in the list. Forecast was not selected at publish, or the artifact is not ready.