Databases and Hypermedia Group, TU/eOther Projects

Food Sales Prediction


Sales prediction is an essential part of stock planning for wholesales and retail business. It is a complex task because of the large number of factors affecting the demand. Designing an intelligent predictor that would beat a simple moving average baseline across a number of products appears to be a not-trivial task.

In our research we work on the development of an intelligent context-aware food sales prediction framework. We study also different aspects of the (cost-sensitive) performance evaluation, and consider the ways of controlling the risks associated with applying intelligent predictors.

We approaching the problem of sales prediction on a case of Sligro Food Group N.V., which encompasses food retail and food service companies selling directly and indirectly to the entire Dutch food and beverages market. The group pursues a multichannel strategy, covering various forms of sales and distribution (cash-and-carry and deliverY service) and using several different distribution channels (retail and wholesale). Sligro has about 60.000 products in stock.

In general, different kinds of the food sales predictions are required for performing different business operations. These kinds include first of all next day, next week, and next month predictions. Daily predictions based on a moving average over different nearest neighbors work reasonably well in this setting and wrong predictions can be often compensated by a human involvement. Weekly predictions are essential for wholesaling of food and food-related products and it is considered to be a more challenging and responsible activity. Therefore, weekly predictions is our current focus.

This research has been partly supported by NWO (HaCDAIS Project) and LOIS (one of TU/e’s eight strategic research areas, that is Logistics, Operations and Information Systems)


Student projects



Unpublished Technical Reports


Presentations & posters