A German fashion manufacturer and retailer has to cope with the dynamic demand for its items in the highly volatile fashion industry. In the fashion industry, volatile demand is an even bigger problem due to comparably high production and transport lead times. The financial risk of overproduction is to be limited to 1%. Demand signals from different markets that differ in forecasting quality are to be integrated.
Low-risk items are identified that have a high probability of future actual orders and recommend an early production start. By bringing forward the production of safe items, the freed-up factory capacity could be used to produce risky items later, when demand signals are more reliable. Machine learning algorithms are applied using historical demand signals, production quantities and item attributes.
A developed R-package is available that recommends specific items and corresponding quantities for all factories by assessing their individual risks and calculating a portion of the original demand signal that is covered with a high degree of certainty.
Are you interested in your own use cases?
Our Case Studies
- Get even more detailed insights into our customer projects -
Smart cooking with the Thermomix
Data Operations at Munich Re
Data & AI Knowledge
Creating added value from data & AI together