Prediction
Before you can use KPI prediction,
KPI history must be enabled. Then, you can enable the prediction functionality
from the KPI Manager.
- Open KPI Manager and select a model.
- Select a KPI and click . The KPI
History and Prediction window opens. Under KPI History,
the Track historical data for this KPI check
box should already be enabled.
- Under KPI Prediction, select the Enable KPI Prediction
based on the historical data for this KPI check box.
- Click New Model to create a prediction
model for this KPI. The Prediction Model Definition window
opens.
- Enter information for the prediction model:
- Enter a name for the model in the Model name field.*
- Under Prediction data points, select the
granularity of data points on the graph.
- For Prediction period, enter the number
of periods for the prediction, or select the To the end
of the KPI time period option.
- Optional: Enable the Include a repeating business pattern option
if you want to capture any repeating patterns (when applicable).
- Click OK to save the model and return to
the Prediction Model Definition window.
- Click OK to save changes and return to
KPI Manager.
- Return to the KPI History
and Prediction widget
and open the configuration options.
- Select the KPI for which you enabled the prediction functionality
and click the History and Prediction tab.
- Under KPI Prediction, enable the Show predictions based
on the following prediction model check box and select
the prediction model from the list.
- Optional: If you want the prediction options displayed on the
graph by default, select the Show prediction data on graph
by default check box.
- Click OK to save changes.
* Limitations in this window could prevent
backspacing and deleting in some fields.