Vorhersage der Verkaufszahlen von gedruckten Zeitungen, u. a. für die BILD und die WELT


Sales Impact

(Technologie-) Partner

Amazon (Amazon SageMaker)



Relevante Passage:

At Sales Impact, a 100% subsidiary of Axel Springer, we are all about sales of print media. We provide regional sales activities and wholesale communication for the supervision of retail sales and the logistics involved for delivery domestic and overseas. Also we do the planning and execution of sales marketing measures, customer acquisition within the scope of direct sales, coordination of the German “Sunday market” and much more.

At my team market analytics, we evaluate, advise and control what happens in the German print media market in terms of sales, logistics and advertisement. This happens at an international, national, regional, wholesale and shop level for print media such as WELT and BILD. My work as a Data Scientist mainly gravitates around the prediction of the market and the calculation of key figures in the market.
Your friend in the cloud
Using Amazon Web Services, we can leverage their machine learning solution Amazon SageMaker in order to make such a prediction. But then, how would you predict some 100,000 shops without losing the information that exists among these shops? Fortunately, there is an algorithm out there that takes into account just this: the Amazon SageMaker DeepAR forecasting algorithm. But this really can be translated to any problem that has at least several hundreds of concurrent time series like e.g. with many products.
With the more accurate prediction of sales, we are able to give even more accurate projections to the editorial departments. Also, we work on taking into account these sales predictions to improve logistical key figures we provide to our business partners.

In this article, we write about predicting newspaper sales using Amazon SageMaker DeepAR. After a short company and team introduction, we give a shallow description of our shop-level sales data and the related problem. We then describe how DeepAR is a suited algorithm for this problem, followed by an overview of our solution together with some sample code to reproduce our solution. Finally, we claim that such a prediction with DeepAR is beneficial to our business.



Apart from retail sector, there are various possibilities of implementing artificial intelligence, prescriptive analytics, and predictive analytics […] Axel Springer tested forcasts of customer cancelling their suscriptions to identify future “cancelers”-the optimal foundation for an efficient customer relationship management.



Prediction of sales rates is a challenging task, since the underlying times series is extremely noisy and bears the danger of over tting easily. At the sametime the large number of data sets, e.g., data from several thousands of retailtraders, allows for a good evaluation of the approach. Furthermore, the real timeprediction system is continously evaluated in practice. The ‘BILD-Zeitung’ is a german newspaper of the Axel Springer Verlag.
The sales department of the Axel Springer Verlag developed a predictionsystem based on neural network models for the time series of each retail traderand improved the return quota of several wholesalers by more than 5%. That isan average reduction of the percental return quota from 16.3% to about 15.5%. S.414-415





Neumann, Justin (2020): Predicting Newspaper Sales with Amazon SageMaker DeepAR. Online verfügbar unter https://medium.com/axel-springer-tech/predicting-newspaper-sales-with-amazon-sagemaker-deepar-dffde3af4b20, zuletzt geprüft am 27.11.2020.



Claßen, Mareike; Milnik, Michael (2019): Big Bang Based Decision Automation. In: Michael Buttkus und Ralf Eberenz (Hg.): Performance Management in Retail and the Consumer Goods Industry. Best Practices and Case Studies. Cham: Springer, S. 165-182. Online verfügbar unter https://books.google.de/books?id=MgGfDwAAQBAJ&pg=PA180&lpg=PA180&dq=%22axel+springer%22+%22machine+learning%22+-akademie+-academy&source=bl&ots=pieKqbJhA-&sig=ACfU3U3bquSg6mF51PhJ3iq3PztETlgkTw&hl=de&sa=X&ved=2ahUKEwjl3cTjlf3rAhWOCOwKHfSZDx04ZBDoATACegQICBAB#v=onepage&q=%22axel%20springer%22&f=false, zuletzt geprüft am 02.11.2020, S. 180.


Ragg, Thomas (2001): Building Committees by Clustering Models Based on Pairwise Similarity Values. In: G. Goos, J. Hartmanis, J. van Leeuwen, Luc de Raedt und Peter Flach (Hg.): Machine Learning: ECML 2001, Bd. 2167.
Berlin, Heidelberg: Springer Berlin Heidelberg (Lecture Notes in Computer Science), S. 406–418.
Online verfügbar unter https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&ved=2ahUKEwi11dyxtOPsAhXGy4UKHXozAgEQFjAAegQIAxAC&url=https%3A%2F%2Flink.springer.com%2Fcontent%2Fpdf%2F10.1007%252F3-540-44795-4_35.pdf&usg=AOvVaw24tB8O571lzG2YeMvvEkMT, zuletzt geprüft am 06.12.2020, S. 414-415.