Eriksson, Mattias
- Department of Energy and Technology, Swedish University of Agricultural Sciences
Report2023Open access
Strotmann, Christina; Gerwin, Paula; Eriksson, Mattias; Wolkow, Roman
This deliverable reports on how the innovation Mitakus, provided by the German company
Mitakus Analytics UG, which aims at reducing food waste in the food service sector, was applied
in the LOWINFOOD project. Mitakus uses sales data provided by the users and combines this with
external factors such as the weather or holidays to calculate a sales forecast. This can help users
plan their production more accurately. Food waste can be reduced if the users avoid producing
surpluses by utilizing the Mitakus forecast.
In Germany, two users tested the Mitakus innovation as part of the LOWINFOOD project. Both
users are university student canteens of differing sizes. This report presents the methodological
approach to testing. The results of an initial food waste measurement in the businesses, an
assessment of the forecasts’ performance, and the results of a survey on user-friendliness and
potential improvements are presented. The innovation was highly affected by the COVID
pandemic. Thus, the demonstration of Mitakus faced several challenges, such as acquiring
businesses for testing or providing usable historical sales figures to create the forecasts. The
opportunities offered by Mitakus included, for example, the company's responsiveness to
customer requirements.
The waste measurement in the businesses discovered that 46 and 41 grams of food were initially
wasted per serving including plate, serving, and preparation waste. The user survey revealed that
the implementation of the app was initially perceived as somewhat difficult. In contrast, use by
management was described as rather simple. The dashboard and its features also received a good
rating. The performance of Mitakus' short-term forecasts is better than those predicted by the
users themselves. In contrast, the quality of the long-term forecast depends on the circumstances
in the company and is strongly influenced by short-term changes to the menu.The current status
of testing is that Mitakus is continuously improving the prediction models created.
Publisher: LOWINFOOD
Business Administration
Software Engineering
https://res.slu.se/id/publ/127587