Food Sales Prediction

About

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)

Collaborators

Mykola Pechenizkiy (TU/e)
Jorn Bakker (TU/e)
Indrė Žliobaitė (U.Vilnius & TU/e)
Toon Calders (TU/e)
Hugo Jaspers (Sligro)

Student projects

Patrick Meulstee (TU/e & Sligro): Food sales prediction: If we only knew what we know
Priyan Vasanthapriyan (TU/e): Cost-sensitive food sales prediction

top

Publications

Žliobaitė, I., Bakker, J. and Pechenizkiy, M. (2012). Beating the baseline prediction in food sales: How intelligent an intelligent predictor is?
Expert Systems with Applications 39(1), p. 806-815. [PDF] [BIB]
Apeh, E., Žliobaitė, I., Pechenizkiy, M., Gabrys, B. (2012). Predicting Customer Profiles Based on Transactions: a Case Study in Food Sales. In: Proc. of the 32nd Annual Int. Conf. of the British Computer Society's Specialist Group on Artificial Intelligence (SGAI'12), Research and Development in Intelligent Systems XXIX, p. 213-218. [PDF] [PDFlong]
Žliobaitė, I., Bakker, J., Pechenizkiy, M. (2009). Towards context aware food sales prediction. In Y. Saygin et al. (Eds.), Proceedings 3nd International Workshop on Domain Driven Data Mining (DDDM'09), in: IEEE International Conference on Data Mining: Workshops (ICDM'09, Miami, Florida, USA, December 6-9, 2009). (pp. 94-99). [PDF] [BIB]
Žliobaitė, I., Bakker, J., Pechenizkiy, M. (2009). Towards context aware food sales prediction. In Y. Saygin et al. (Eds.), Proceedings 3nd International Workshop on Domain Driven Data Mining (DDDM'09), in: IEEE International Conference on Data Mining: Workshops (ICDM'09, Miami, Florida, USA, December 6-9, 2009). (pp. 94-99). [PDF] [BIB]
Bakker, J., Pechenizkiy, M. (2009). Food wholesales prediction : what is your baseline? In J. Rauch, Z.W. Ras, P. Berka, T. Elomaa (Eds.), Foundations of Intelligent Systems (18th International Symposium, ISMIS 2009, Prague, Czech Republic, September 14-17, 2009. Proceedings). (Lecture Notes in Computer Science, Vol. 5722, pp. 493-502). Berlin: Springer. [PDF] [BIB]
Meulstee, P., Pechenizkiy, M. (2008). Food sales prediction: "If only it knew what we know". Proceedings 2nd International Workshop on Domain Driven Data Mining (DDDM'08), in: IEEE International Conference on Data Mining: Workshops (ICDM'08, Pisa, Italy, December 15-19, 2008). (pp. 134-143). IEEE Computer Society. [PDF] [BIB]

Unpublished Technical Reports

Žliobaitė, I., Bakker, J., Pechenizkiy, M. (2010). Beating the baseline prediction in food sales: How intelligent an intelligent predictor is? (SIGKDD2010 Submission, Industry track).
Žliobaitė, I., Bakker, J., Pechenizkiy, M. (2010). Context Aware Sales Prediction: experimental evaluation. (TR-Feb2010.pdf).
Žliobaitė, I., Bakker, J., Pechenizkiy, M. (2009). Towards Context Aware Sales Prediction. (TR-Sep2009.pdf, extended version of DDDM'09 submission).
Žliobaitė, I. (2009). On Recognition of Seasonal Predictability in Food Product Sales. (TR-Jul2009.pdf).

top

Presentations & posters

Towards context aware food sales prediction. The 3rd International Workshop on Domain Driven Data Mining (DDDM’08 at IEEE ICDM 2009), Miami, Florida, US (December 2009).
Towards context aware food sales prediction. Poster presented at 21st Benelux Conference on Artificial Intelligence (BNAIC'09), Eindhoven, The Netherlands (October 29-30, 2009).
Food wholesales prediction: what is your baseline? 18th International Symposium on Methodologies for Intelligent Systems (ISMIS 2009), Prague, Czech Republic (September 14-17, 2009).
Food Sales Prediction: “If Only It Knew What We Know”. The 2nd International Workshop on Domain Driven Data Mining (DDDM’08 at IEEE ICDM 2008), Pisa, Italy (December 2008).

top