In our project we use the sale information of 53 articles of the same product group in a supermarket.
The information about the number of sold articles and the sales revenues in DM are given weekly
starting September 1994.
In addition there are advertising campaigns for articles often combined with temporary price reductions.
Such a campaign lasts about two weeks and has a significant influence on the demand on this article.
The sale and average price for one article are shown in figure 
.
Figure 2: sale of article with advertising
The aim is to forecast the sale of an article for the next week by neural networks. For prediction the past information of n recent weeks is given to the input layer. The only result in the output layer is the sale for the next week. So there is a window of n weeks in the past and one in the future. Both the input and output together are called a training pair. One training of all training pairs is called an epoch.
Because all the considered articles belong to one product group, we have a quite constant sales volume of all products. An increasing sale of one article leads to a decrease of the other products. Because of this reason, we train one neural net for the prediction of each article with the information of all articles in the input layer. We have the three items sale, advertising and price for three weeks in the recent past for 53 articles. So our nets have nearly 600 input neurons and between 50 to 100 neurons within the hidden layer. This leads to enormous training times.