Why create forecasts at an aggregate level

For the reasons listed below, it may be worthwhile to create your forecasts at an aggregate level and not at the item level, the default platform setting.

  • Forecast accuracies are always better when forecasts are calculated from larger volumes.

  • If your business regularly replaces certain items with more recent versions (eg if you sell mobile phones), it is difficult to detect seasonality and trends, due to the short product life cycle. One way to improve your forecasts is to create them from the product family level since new articles replace older ones.

To do this, go to the Forecast Edition tab.

Display your data in an aggregated format

Let's create an aggregation at a specific level, such as product family. If you have defined custom fields in your account, you should see them listed here. You can use any combination of fields to create an aggregation.

Click the icon Aggregation fields...

First, we must select the field for your aggregation. Here we select Family.

Click Confirm to compute the aggregation.

Your data are automatically summed to display the relevant aggregations.

How to calculate forecasts at an aggregate level

In addition to displaying your aggregations, you have the option to recalculate all forecasts contained in the current list of aggregations. In order to apply this different calculation method only to certain items, you just need to filter the data to only retain the relevant aggregations in your table.

To launch a new computation of your forecasts from this level, click on the calculator icon.

The following pop-up window appears. If you want to update all the forecasts contained in your selection, click Forecast at aggregate level, otherwise click Close.

By clicking on Forecast at aggregate level, the platform automatically launches a series of calculations.

It begins by calculating the best forecast for each product family.

Then from this forecast created at the product family level, it automatically distributes each value found for each period, at each lowest-level forecast as defined in your account.

If your lowest level forecasts are set at the SKU level, the platform will update all SKU level forecasts with the new data from that top level calculation.

If your lowest level forecasts are set at the SKU / Customer level, all of those forecasts will be updated accordingly.

Example from the demo account

Using the data from the demo account, it is possible to quickly understand the platform behavior.

Below, the platform displays the forecast for Family 4 before launching the calculations at the family level. The forecast displayed is the sum of all the forecasts of the constituent articles of family 4. In this case the forecasts have been calculated at the article level.

If we run the forecast calculation at the family level, we get the result below for the family. We can see graphically that the result is different for family 4. The more items you have in your aggregation, the more visible the impact will be on your forecasts. On the demo account, the number of references is reduced, so the impact is slight.

How to compute the forecast at the lowest level

To cancel the effect of this calculation at the aggregate level, simply deselect the aggregation, to see the forecasts at the lowest level, and restart the forecast calculations at this level.

Click Confirm to get rid of your aggregations

.

By clicking on the calculator again, you see this window.

Click Confirm & Launch to calculate the forecast at the level defined in your account.

Did this answer your question?