Running a Predictive Time Series Forecast

Using data from a planning model, you can run a time series forecast on a single cell in a table.


You will need planning rights and a planning license to run a predictive time series forecast.


  1. Open or create a new story, and add a table based on a planning model to a story page.
    • In the Builder panel, add a time dimension if none is currently included as a Column.
  2. Select a single cell that can be edited. From the story toolbar, select the (Forecast) icon.

    The Set Predictive Forecast dialog is displayed.

  3. Under Forecast, specify the period you want to forecast.

    The Forecast by value specifies the time granularity for the predictive forecast. Select Show more options to see more settings for the forecast. Use Past Period From specifies the starting point for the predictive forecast calculation. Reference Period indicates the date of the last booked data for the context you are forecasting.

    Forecast by will be the lowest granularity available in the model, if no time values are available in the table.
  4. When you are ready to run the predictive forecast, select Preview.

    The time series forecast is displayed in the Preview Predictive Forecast dialog. The preview contains the past actual values together with predicted values displayed as a graph and a table row. Upper and lower limits for the confidence interval are also provided for the graph. The table rows contain the predicted values that will be added to the table. A dashed line (originating from the first point of the forecast) represents the predictive model applied to past periods.

    You can preview the existing values and predicted values for booked cells after running a time series forecast. Before populating the table in the story, you can choose to either keep or overwrite the weighting of leaf members for selected cells.
    1. Select a booked cell in the predicted values table.
    2. Chose a weighting option for the cell.

      If you select Use existing weighting for overwritten values values will be assigned to leaf members using the existing weighting. If you select Use reference period's weighting for overwritten value, values will be assigned to leaf members using the reference period's weighting.

  5. To populate the table with the forecasted values, select OK.

    A message indicates that the forecasted values were added to the table.