Reliable sales forecasts are at the heart of the supply chain. Only with an accurate assessment of future sales quantity can material requirements and machine capacities be planned in good time.
If this is done in a rolling manner, the planner gains increasing certainty about the real-time situation in terms of material and machinery over time.
A simulation enables the assessment of worst and best case scenarios. This makes it easy to simulate external and internal influences on demand planning.
It is important to include as much information as possible that has an influence.
This includes not only valid information from marketing and sales but also information about events, customer assessments, management guidelines and much more.
The key functions of the Forecast solution
- Integration of external sources of information
- A quick assessment of developments through meaningful graphics
- Simulate different future scenarios
- A top current database for all
- Individual evaluation options
For optimal demand planning, data from the past must be interpreted correctly to be able to make valid forecasts for the future. The ifm software uses various statistical methods for this purpose. The illustrations show that not every forecasting method optimally extrapolates reality.
The figures show two different forecasting methods that are supposed to update the actual state of the development. It becomes clear that both methods are not suitable for providing valid information on sales development. The actual value of the past (shown as blue columns) shows significant fluctuations that the forecasting methods do not capture.
In this figure, the Additive Model, better known as Prophet method, is shown as a green line.
Prophet emerges as the winner: the past observation converges convincingly well and suggests with a high degree of certainty a reliable extrapolation.
The unsuitable Median and Croston methods are also included in the presentation as light blue and dark blue columns.
The possibility of combining different forms of presentation in one figure enables the user to make an easy assessment. "See and understand" – this is how it is often possible to see at first glance who will emerge as the winner.
The solution takes into account different sources such as marketing, sales or even from the customer side itself to be able to create a comprehensive picture.
The database is always up to date and can be viewed by all participating departments and supplemented with information – this means the end of "excelitis" and interfaces.
As pictures say more than a thousand numbers, ifm's software presents even complex issues such as the forecasting procedures graphically; so they can be grasped at a glance.
To be able to produce optimal forecasts in the long term, the forecasting process must be continuously scrutinised:
- Were the correct forecasting methods chosen?
- Have the correct sources been integrated?
- Is the information weighted correctly?
- Is the planning close to reality?
After all, demand planning should work according to the principle: "Planning without control is pointless. Control without planning is impossible."
Only those who recognise their mistakes can improve – by the way, this applies to humans just as much as to artificial intelligence.
Even with 80% of planned materials, demand planning can produce disastrous results.
Because if, of all things, 20% of unplanned materials make up the majority, planning becomes a product of chance.
So how can the relevant materials be determined?
Good planners often already have different versions of the future in mind, since the occurrence or non-occurrence of certain events results in different possible scenarios.
It is therefore advantageous to plan the different scenarios and to calculate the respective effects on the demand plan.
This way, you always have the famous "plan B" in your pocket.
How do I forecast a realistic update of the expected sales quantity?
The ifm solution suggests the forecast model that best fits your data series. An extensive forecast pool ensures that a sufficient number of forecast models are available to achieve a truly accurate result.
How do I make sure I have a "Plan B" in my pocket in case the foreseen event does not happen in the future?
Experienced demand planners calculate upcoming events, knowing full well that there are various future scenarios. The simulation function of the forecast solution makes it possible to run through different scenarios in advance and thus assess the respective impact on demand and capacity planning.
How do I guarantee that special and one-off effects are not carried forward into the future?
The forecast solution offers the automatic correction of outliers. This ensures that the planning result is not distorted.
How do I make sure that other organisational units, e.g. sales, plant, and production, also benefit from demand planning?
Through the free definition of planning hierarchies and the possibility of selecting different organisational units, each department can set its individual view of demand planning and thus derive its own goals and to-dos.
Nevertheless, all departments work with the same database!
How do I ensure that all relevant factors are taken into account in demand planning?
The forecast solution offers the possibility to integrate external data sources. For example, Excel calculations from sales, marketing or customers can be included.
You are already using our forecast solution, but are wondering what new features the current release offers?
Then our colleague Roman Bernikov, Software Developer Forecast, will be happy to introduce you to the new functions.