Configuration

This section explains each of the properties in the configuration blade.

General

PropertyDescription

Collection

This associates the Agent to a specific Collection (default to that of the current Data Stream).

Refer to Collections and Stream Hosts to understand more about Collections.

Training

PropertyDescription

Label Field

The value to forecast.

Interpolate Time

Tick to calculate Date-time values for the forecast values.

These properties apply when Interpolate Time is checked.

PropertyDescription

Timestamp Field

Timestamp field in the data used to interpolate future Date-time values

Frequency

Time interval between two values.

Unit

Unit of time interval options: Seconds, Minutes, Hours, Days, Weeks, Months, Years.

Algorithm Parameters

PropertyDescription

Forecast Horizon

The number of predictions to make in advance.

Series Length

The number of data points to remember and use to perform a forecast.

Window Size

The number of data points in a regular cycle.

Confidence

The confidence level of forecasting.

Model Options

PropertyDescription

Deterministic Seed

Set this to a whole number for repeatable/deterministic results across multiple trainings.

Before configuring the Agent, please ensure that its input endpoint is connected to a parent Agent which will be sending data to it.

Endpoints

NameDescription

Input

This endpoint is used to receive data from the parent Agent.

Output

Events received by the parent Agent and forecast values are made available to this endpoint.

Last updated