The catering service Stattküche in Münster produces around 22,000 parts of lunch every day, providing them to schools and nurseries. A part of pre-ordered meals, nevertheless, is routinely not collected, because cancellations show up far too late or are forgotten entirely. For hygiene reasons, this food typically needs to be disposed of.
Therefore, in partnership with the Center for Entrepreneurship and Transfer (CET) at TU Dortmund University and Stattküche, Dr. Ina Dormuth and Teacher Markus Pauly developed a forecasting technique using Expert system (AI), so that production can be flexibly gotten used to real everyday demand. To attain this, they initially processed comprehensive historical order information and integrated it with parameters such as public holidays, weather conditions, and information on influenza waves. They then evaluated different analytical and artificial intelligence methods, ultimately designing a tool that analyses historical order patterns and supports future portion planning by forecasting expected cancellations as specifically as possible. In this method, food waste is to be decreased, resources utilized more effectively, and expenses decreased. The digital application has considering that been integrated into Stattküche’s everyday workflows and supports the massive cooking area in its decision-making in a transparent, data-driven manner.
Methodologically Sound and Virtually Suitable
The difficulty for the job team lay in establishing a technique that was both methodologically sound and practically applicable: How can one learn from previous order and cancellation patterns? How can different forecasting approaches be compared? And how can the results be made functional for individuals who plan meals every day? “Our goal was to deploy scientific methods in such a method that they genuinely assist in the daily running of a large-scale kitchen. The award reveals that data-driven solutions can make a concrete contribution to greater sustainability,” states Teacher Markus Pauly of the Department of Data, who is likewise a scientist at the Research Center Trustworthy Data Science and Security of the University Alliance Ruhr. Dr. Ina Dormuth, who performed the core analytical work as a former doctoral and postdoctoral researcher at Teacher Pauly’s chair, has been working as a Data Researcher in the Research and Advancement department of the Wilo Group because 2026.
The job “AI Instead of Waste” was supported by the European Digital Development Hub Dortmund (EDIH-DO). This consortium, with the involvement of CET and TU idea GmbH, assists small and medium-sized business to expand their digital competencies and to implement transfer tasks from research into practice. The Center is co-financed by the EU and types part of the network of European Digital Innovation Hubs.
The “EDIH Network Award for Excellence 2026” existed in early June at the EDIH Top in Brussels. With its innovative method, its tangible impact, and its transferability to other fields of application, the EDIH-DO and “AI Rather of Waste” had the ability to prevail over the two other finalists. An overall of 69 jobs had actually been submitted.
Contact person for queries: