The catering service Stattküche in Münster produces around 22,000 portions of lunch every day, providing them to schools and nurseries. A part of pre-ordered meals, nevertheless, is regularly not collected, since cancellations arrive too late or are forgotten completely. For health factors, this food generally has to be dealt with.
For that reason, in cooperation with the Center for Entrepreneurship and Transfer (CET) at TU Dortmund University and Stattküche, Dr. Ina Dormuth and Teacher Markus Pauly established a forecasting method utilizing Artificial Intelligence (AI), so that production can be flexibly adapted to real everyday need. To attain this, they initially processed substantial historical order data and integrated it with specifications such as public vacations, climate condition, and data on influenza waves. They then checked numerous statistical and artificial intelligence methods, ultimately designing a tool that analyses historical order patterns and supports future portion planning by predicting expected cancellations as specifically as possible. In this method, food waste is to be minimized, resources utilized better, and expenses decreased. The digital application has given that been integrated into Stattküche’s day-to-day workflows and supports the massive kitchen in its decision-making in a transparent, data-driven way.
Methodologically Sound and Almost Applicable
The challenge for the project group lay in developing a method that was both methodologically sound and practically suitable: How can one gain from previous order and cancellation patterns? How can different forecasting techniques be compared? And how can the results be made functional for people who prepare meals on a daily basis? “Our goal was to release clinical techniques in such a way that they truly assist in the everyday running of a massive kitchen. The award shows that data-driven options can make a concrete contribution to greater sustainability,” says Teacher Markus Pauly of the Department of Stats, who is likewise a researcher at the Research Center Trustworthy Data Science and Security of the University Alliance Ruhr. Dr. Ina Dormuth, who carried out the core analytical work as a previous doctoral and postdoctoral scientist at Professor Pauly’s chair, has actually been working as an Information Scientist in the Research study and Development department of the Wilo Group considering that 2026.
The task “AI Rather of Waste” was supported by the European Digital Development Hub Dortmund (EDIH-DO). This consortium, with the involvement of CET and TU principle GmbH, assists small and medium-sized enterprises to broaden their digital competencies and to carry out transfer tasks from research into practice. The Center is co-financed by the EU and kinds part of the network of European Digital Development Hubs.
The “EDIH Network Award for Quality 2026” existed in early June at the EDIH Top in Brussels. With its innovative approach, its concrete impact, and its transferability to other fields of application, the EDIH-DO and “AI Rather of Waste” had the ability to dominate the two other finalists. A total of 69 projects had been submitted.
Contact person for questions: