Example

This example Data Stream demonstrates how to use the Forecasting Agent to predict the value in the future.

Refer to configuration to understand all configuration options of this Agent.

Step 1: Add the Agent

Drag the Forecasting Agent onto the canvas, link the input endpoint to the test data, the output to the printer, save the Data Stream.

Step 2: Configure General

Select the Agent and click Configure. In this case, keep the default Collection.

Step 3: Configure Training

Set the label field to Vertical_Travel and tick the Interpolate Time checkbox. This allows us to calculate DateTime values based on previous data DateTime values.

Set Timestamp Field to DateTime, leave the frequency as 1, and set Unit to Days.

This allows us to read the last DateTime value in the data and Interpolate time for the forecast values.

Step 4: Configure Algorithm Parameters

In this case, set the Algorithm Parameters to the following values:

  • Forecast Horizon: 3

  • Series Length: 30

  • Window Size: 7

Step 7: Results

Apply the changes, save the Data Stream and publish it.

Click Live View to see the output of the Agent. Observe that the parent Agent output is printed, followed (on the last page) by the forecast values predicted by our Agent.

Files

See the Import, Export, and Clone - XMPro article for steps to import a Data Stream.

Last updated