This module is only available in the Enterprise Edition.
This module provides the functionality to manage the forecasted
customer demand. An overview presentation of the module is
available at http://frepple.com/frePPLe_forecasting.pdf
It provides the following capabilities to support the forecasting process
in your company:
Statistical forecast calculation to extrapolate historical demand
into the future
A first step in the process is to collect the historical demand and
run a time series analysis to predict the future demand.
FrePPLe implements the following classic time series methods:
- Single exponential smoothing, which is applicable for constant demands
- Double exponential smoothing, which is applicable for trended demands
- Holt-Winter’s exponential smoothing with mutiplicative seasonality, which
is applicable for seasonal demands
- Croston’s method, which is applicable for intermittent demand (i.e. demand
patterns with a lot of zero demand buckets)
- Moving average, which is applicable when there is little demand history
The algorithm will automatically tune the parameters of each of these
methods to minimize the forecast error.
During the calculation the algorithm scans for exceptional demand outliers,
and filter them out from the demand history.
The algorithm also automatically selects the most appropriate forecasting
method. The user has the ability to override this automatic selection.
FrePPLe also provides the possibility to aggregate the demand at a parent level,
calculate the forecast at this aggregated level, then disaggregate the forecast over
the children. The goal of such a feature is to lay out some patterns such as trend or
seasonality that might not be detected at lower level.
The statistical base forecast is normally computed in batch mode.
Forecast review and manual corrections
In a second step users will review the statistical forecast proposed by
the system. Users have the ability to override the forecast, and apply
their business knowledge (eg new products, products phasing out,
promotions, competition, etc…) to come up with the final sales forecast.
See forecast report.
The process of reviewing the sales forecast is typically a weekly or
monthly process, involving both the sales and production departments.
Preprocess the sales forecast for production planning
The sales forecast needs some preprocessing to make it suitable for the
Profiling the forecast in smaller time buckets
This functionality allows to translate between different time
The forecast entered by the sales department could for instance be
in monthly buckets, while the manufacturing department requires the
forecast to be in weekly or even daily buckets to generate accurate
manufacturing and procurement plans.
Another usage is to model a delivery date profile of the customers.
Each bucket has a weight that is used to model situations where the
demand is not evenly spread across buckets: e.g. when more orders
are expected due on a monday than on a friday, or when a peak of
orders is expected for delivery near the end of a month.
Consuming/netting the forecast with actual sales orders
As customer orders are being received they need to be deducted
from the forecast to avoid double-counting it.
For example, assume the forecast for customer A in January is 100
pieces, and we have already received orders of 20 from the customer.
Without the forecast netting the demand in January would be 120 pieces,
which is (very likely) not correct.
The netting solver will subtract the orders of 20 from the forecast resulting in a net forecast of 80.
The total demand that is planned in January will then be equal to
100 corresponding to 80 from net forecast plus 20 from actual orders.
The netting algorithm has logic to match a demand with the most
appropriate forecast at the right level in the customer and product
hierarchies, and it can also consider netting in previous and subsequent
This process step is recalculated as part of the production plan
Detailed documentation of the module and its configuration parameters is available on our customer portal.