Sales Rate Prediction and Automatic Disposition

In this joint project with the Axel-Springer-Verlag, we develop a system based on machine learning techniques aimed at predicting the daily sales rates of newspapers. The prediction is individually done for every retail trader. The task comprises the forecast of thousands of timeseries differing in many facets like the length of the given history, the average sales level, the noise ratio, seasonal changes, and individual characteristics of the respective retailer. To deal with this task, we use a neural prediction model which is both adaptive to every retail trader and general enough to minimize the individual engineering effort. The model is trained on the daily sales in past and thus adapts to the individualities of each retailer. The prediction of future sales figures simplifies to the evaluation of a mathematical function. The new approach was tested so far on two thousand retail traders of the Bild-Zeitung and results in a significant reduction of the prediction error compared to conventional forecasting algorithms. Our current research is aimed at the further improvement of the prediction model, as well as the extension to the prediction of sales rates of magazines.


This ongoing project has begun in 1996 at the University of Karlsruhe under the direction of Prof. Dr. Wolfram Menzel. Since 2002 it is handled under the direction of Prof. Dr. Martin Riedmiller.

Industrial Partners

The Axel-Springer-Verlag is the biggest newspaper publisher in Germany. It sells about 4.1 million copies of the Bild-Zeitung, the most highly circulated daily newspaper in Germany. It is sold in round about 110,000 sales outlets. Furthermore, the Axel-Springer-Verlag publishes a great number of other daily and weekly journals and magazines.


Researchers working in our team:

  • Prof. Dr. Martin Riedmiller
  • Sascha Lange

Former members of our team:

  • Prof. Dr. Wolfram Menzel, University of Karlsruhe
  • Dr. Martin Lauer
  • Dr. Thomas Ragg


  • Martin Lauer, Martin Riedmiller, Thomas Ragg, Walter Baum, Michael Wigbers: The Smaller the Better: Comparison of Two Approaches for Sales Rate Prediction in: M. R. Berthold, H.-J. Lenz, E. Bradley, R. Kruse, C. Borgelt (eds), Advances in Intelligent Data Analysis V pp. 451-461, Springer, 2003
  • Thomas Ragg, Wolfram Menzel, Walter Baum, Michael Wigbers: Bayesian Learning for sales rate prediction for thousands of retailers, Neurocomputing, 43:127-144, 2002
  • Thomas Ragg, Wolfram Menzel, Walter Baum, Michael Wigbers: Predicting Sales Rates for Thousands of Retail Traders, in: Proc. of the Int'l Conf. on Engineering Applications of Neural Networks pp. 199-206, 2000


For more information on this research project, please contact Martin Riedmiller.