WAZ Media Group optimizes subscriber marketing

Published on 17-Nov-2011

Validated on 02 May 2013

"While in the past we had to wait hours for some analyses of large data volumes, today they are ready within a minute. Thus, the new technology is immediately being transformed into commercial success. And the great flexibility of the IBM SPSS Modeler solution offers us huge future potential." - Dr. Ana Moya, Sales Management, Reporting and Analysis department, WAZ

Customer:
WAZ Media Group

Industry:
Media & Entertainment

Deployment country:
Germany

Solution:
BA - Business Analytics, BA - Business Intelligence

Smarter Planet:
Smarter Media

Overview

Headquartered in Essen, Germany, and employing some 15,000 people, the WAZ Media Group is one of Europe’s leading media enterprises. With 13 printing operations in Germany and abroad, the company publishes 27 newspapers and 13 weekly papers, 175 consumer magazines and technical periodicals, 99 free papers and 400 customer magazines.

Business need:
The WAZ Media Group wanted to make better use of its extensive collection of information about its subscribers and readers to improve its marketing efforts and remain competitive in the tough media industry.

Solution:
WAZ Media Group chose IBM® SPSS® Modeler and used its comprehensive functionality and high performance to provide sophisticated statistical tools for analysing large volumes of data, driving greater marketing efficiency and delivering lower costs.

Benefits:
Reduced coverage resulted in more efficient marketing activities with better response rates. Provides continuous improvements to WAZ Media Group’s products and services.

Case Study

To read a German version of this case study, click here.

Headquartered in Essen, Germany, and employing some 15,000 people, the WAZ Media Group is one of Europe’s leading media enterprises. With 13 printing operations in Germany and abroad, the company publishes 27 newspapers and 13 weekly papers, 175 consumer magazines and technical periodicals, 99 free papers and 400 customer magazines.

The enterprise publishes 10 regional newspapers in North Rhine-Westphalia, Thuringia and Lower Saxony. Four North Rhine-Westphalia titles (“Westdeutsche Allgemeine Zeitung” (WAZ), “Westfälische Rundschau” (WR),”Neue Ruhr / Neue Rhein Zeitung“ (NRZ) and “Westfalenpost” (WP)) have a print run of about 870,000 copies. The free papers of the WVW/ORA are market leaders in Germany and Europe, with a weekly print run of more than 5 million copies in North Rhine-Westphalia alone.

The WAZ Media Group also has majority holdings in eleven local radio stations in North Rhine-Westphalia and runs Germany’s biggest regional Internet portal, DerWesten.de. The company has stakes in NRW.TV and the Albanian station, Vizion +. It is a part owner of the Munich Gong Publishing house (“Gong”, “TV direkt“) and the WAZ-Women Group (“Neue Welt”, “Frau im Spiegel“), as well as numerous animal magazines, puzzle magazines and technical periodicals.

Beyond Germany, the WAZ Media Group operates in the Austrian newspaper market (“Kronen Zeitung“, “Kurier”), as well as in Albania, Croatia, Macedonia, Russia, Serbia and Hungary.

The vision: better utilisation of information increases commercial success
In 2009, the WAZ Media Group began to evaluate its extensive collection of information about its subscribers and readers more systematically. Its aim was to increase insight into customer behaviour in order to improve its marketing strategy. At first, the company tentatively used analytics and statistics software from the Open Source area. However, after a short time, the company’s need for information outpaced the capabilities of this software, prompting WAZ Media Group to search for a new statistical package. A number of major statistics software providers were considered, and IBM SPSS® Modeler was one of the products evaluated.

At this time, Dr. Ana Moya, a data mining expert with a doctorate in statistics, joined WAZ Media Group as a member of the Sales Management, Reporting and Analysis department. One of Dr. Moya’s first duties was to look for a software solution. The potential solution would have to meet high demands, including frequent daily use, huge data processing volumes and complicated task settings. Not least because of her long-standing expertise, Dr. Moya played a key role in the selection of a new software solution for the WAZ Media Group.

“I was impressed by the possibilities that the IBM software offered,” says Dr. Moya, regarding IBM’s presentation of the SPSS Modeler solution. Following the initial demonstration, IBM provided a test version of the software, which was carefully examined and used for some test calculations. The software’s intuitive user interface allowed initial models to be evaluated quickly, and enabled different parameter settings to be tested on the chosen models. Even at this early stage, the software proved to be extremely flexible with various queries.

Dr. Moya had extensive knowledge of many different statistics solutions, as a result of her time spent at the University of Dortmund and at various enterprises, and recognised the potential of the IBM solution. After running extensive tests of IBM SPSS Modeler she was persuaded: “This software is fun from the first go. The intuitive user interface with its icons and graphic elements invites the user to interactively develop models on the screen. The graphics and tables that are provided are extremely clear and therefore very well-suited for strong presentations. Moreover, we could be sure that we were getting a reliable, established product, as much time has been devoted to its development. Finally, its handling of large data volumes was impressive – we have data from several million customers at our disposal, and the software can typically produce results in a few seconds.”

In addition, the breadth and accuracy of the solution’s scientific models were very important criteria that motivated the decision in favour of IBM SPSS Modeler.

IBM SPSS Modeler: rapid installation and instant results
The IBM SPSS solution currently receives data from an Oracle database. In future, the data supply will be provided via a connection to SAP NetWeaver Business Warehouse.

Improving marketing campaigns and reducing waste coverage costs with customer segmentation
Key application areas of IBM SPSS Modeler at WAZ Media Group include response analysis and the measurement of advertising effectiveness. Past marketing campaigns and advertisements are systematically evaluated by examining, for example, which customers have responded by each communication channel, or which customer groups have responded most frequently to which offers. It is also possible to compare the behaviour of active subscribers, former subscribers and one-time buyers. For these comparisons, ‘supervised learning’ algorithms are usually applied. This allows users to not only predict the output variable, but also to measure the influence of the input variables. Then the quality of the resulting model can clearly be illustrated by tools such as “lift and gain” charts.

The knowledge obtained allows detailed customer segmentation with different input variables such as, for example, preferred contact channel, housing situation or the usual socio-demographic criteria like age, gender, marital status or income. It is also possible to classify subscribers according to models based on ‘unsupervised learning’ techniques. With the help of the SPSS software, different types of cluster analyses can be easily compared with each other, and the user decides in favour of the model which delivers the smallest forecasting error. The classifications allow the company to identify typical readers of its different newspapers by their common characteristics. The results can provide interesting conclusions.

For example, information gained about the most common interests of typical Westdeutsche Allgemeine Zeitung readers reveals other products that they might be interested in. In this way, the marketing department can predict which communication channels will produce the highest level of response from various customer segments.

“Even though we have not been using the new statistics solution for very long, the whole team is deeply impressed by its explanatory power and the benefits to be gained from the enhanced insight it provides,” reports Dr. Moya. “The sales teams are already profiting greatly from it. As we can now tell which groups of customers represent the highest prospects of success, we can substantially reduce the waste coverage costs of our campaigns and simultaneously maximise response rates. This will give us a significant competitive advantage in the industry.”

Systematic analysis supports proactive marketing
Churn management is another area where the new analytics solution is helping WAZ. The solution analyses data from customers who have unsubscribed in order to find out why they chose to cancel their subscription, and to identify possible common characteristics of such ex-customers.

“Equipped with this knowledge, we can evaluate our data in a more targeted way and work towards preventing attrition,” explains Dr. Moya. “We can identify customer groups that have a potentially higher likelihood of drifting, and we can implement measures to counteract them in a timely manner. This helps us prevent larger declines by engaging in appropriate customer retention or win-back activities.”

Further information can be garnered from the combination of socio-demographic and location-based analyses obtained from other applications used by the WAZ Media Group. “Because we have learned that, for example, different affinities exist in certain population groups and regions, we are able to considerably lower the waste coverage costs and, at the same time, increase the response rates with our subscription campaigns,” Dr. Moya states.

Huge potential for the future
“Although it’s still too early to quantify the results of our business analytics solution, one thing that is already certain is the huge time-saving,” says Dr. Moya. “While in the past we had to wait hours for some analyses of large data volumes, today they are ready within a minute. Thus, the new technology is immediately being transformed into commercial success. And the great flexibility of the IBM SPSS Modeler solution offers us huge future potential.”

About IBM Business Analytics
IBM Business Analytics software delivers actionable insights decision-makers need to achieve better business performance. IBM offers a comprehensive, unified portfolio of business intelligence, predictive and advanced analytics, financial performance and strategy management, governance, risk and compliance and analytic applications.

With IBM software, companies can spot trends, patterns and anomalies, compare “what if” scenarios, predict potential threats and opportunities, identify and manage key business risks and plan, budget and forecast resources. With these deep analytic capabilities our customers around the world can better understand, anticipate and shape business outcomes.

Products and services used

IBM products and services that were used in this case study.

Software:
SPSS Modeler

Legal Information

© Copyright IBM Corporation 2011 IBM Deutschland GmbH 71137 Ehningen Deutschland ibm.com/de IBM Österreich Obere Donaustrasse 95 1020 Wien ibm.com/at IBM Schweiz Vulkanstrasse1068010 Zürich ibm.com/ch Produced in Germany November 2011 All Rights Reserved IBM, the IBM logo, ibm.com, and SPSS are trademarks of International Business Machines Corporation, registered in many jurisdictions worldwide. A current list of other IBM trademarks is available on the Web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.shtml. Other company, product or service names may be trademarks, or service marks of others. References in this publication to IBM products, programs or services do not imply that IBM intends to make these available in all countries in which IBM operates. Any reference to an IBM product, program or service is not intended to imply that only IBM’s product, program or service may be used. Any functionally equivalent product, program or service may be used instead. All customer examples cited represent how some customers have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics will vary depending on individual customer configurations and conditions. IBM hardware products are manufactured from new parts, or new and used parts. In some cases, the hardware product may not be new and may have been previously installed. Regardless, IBM warranty terms apply. This publication is for general guidance only. Photographs may show design models.