FALKE
Forecast optimization with machine learning
Since 1895, the family business FALKE has stood for fashionable clothing made from high-quality materials, processed with perfect craftsmanship and attention to detail. The company produces sweaters, bodysuits, tights and stockings, underwear and sportswear.
In order to guarantee the availability of products worldwide, the expected sales must be planned accordingly. Together with celver, FALKE has already introduced a sales planning system based on Board, the results of which are then incorporated into production planning.
However, as the forecast quality of the statistical method used was not sufficient, the sales planners had to repeatedly intervene manually to obtain plausible results. A forecast method was therefore sought that would provide more reliable data and thus reduce the workload for the specialist department.
The facts at a glance
Advantages and benefits
- Simplification of the planning process
- Less manual effort
- Increase in forecast quality by 21
- High user acceptance thanks to improved results in the familiar system
- Trust in the data
By integrating state-of-the-art programs such as R and Python as well as open source components into our existing solution architecture, we were quickly able to significantly improve the forecast quality.
