Poland's leading telco retains more customers using SAS® and Teradata

Telekomunikacja Polska has evolved from a national monopoly to an agile player in a highly competitive free market. With company earnings under pressure due to falling prices and declining customer loyalty, there's a great need to understand customer behavior in order to diminish soaring churn rates. SAS and Teradata provide an analytical platform that has enabled Telekomunikacja Polska to slow down the negative trend - and to achieve significant savings.

For many years, Telekomunikacja Polska was Poland's only telecommunications company. But once the former Eastern Bloc nation joined the European Union - and the national monopoly was acquired by France Telecom Group - the winds of change blew through the company. Since then, the company has competed in a free and open market. Still Poland's largest telephone company by far, Telekomunikacja Polska now has almost 7.5 million fixed lines and approximately 22,500 employees. But competition and changing consumer behavior are putting the company under pressure - especially in the landline segment, which is Telekomunikacja Polska's primary source of income.

Although they are still the market leader, with a 71 percent market share in fixed lines and 39 percent in broadband services, the company has seen more than 1 million customers walk away to buy their landline services from a competitor. And more and more customers are choosing to drop their landlines altogether in favor of their mobile phones. Telekomunikacja Polska management thus maintains focus on customer retention and decided to invest in campaign activities to minimize the risk of customer churn.

Cost savings potential
Telekomunikacja Polska chose SAS as their strategic supplier for an analytical application that creates insight into customer behavior and helps to predict churn. The SAS solution transforms hard operational data into valuable knowledge for staff in departments dealing with customers, giving them detailed information on individual customer behavior patterns.

"SAS gives us dimensions of insight that enable us to better manage our retention activities," says Jarosław Kosiński, Corporate Project Manager with responsibility for the Churn Prediction Model project and DWH project at Telekomunikacja Polska. "With so many landline customers, there is a real risk of spreading our efforts too thin. SAS tools help us react with good offers to our core customers as soon as they show the very first signs of churn. The effects are measurable - substantial cost savings that we can track right down to the bottom line."

From business to mass-market customers
According to Kosiński, the project began by focusing on business customers, where customer profitability is highest. With the help of SAS tools, Telekomunikacja Polska selected the most profitable business customers to test the data mining methods. The company is now expanding the project to include the mass-market customers.

"In spite of economic crisis, our management has decided to extend and expand the BI projects since they have so much strategic importance for our profits and market position. With our integrated SAS and Teradata environment, we are able to compete in a falling landline market. The customer insight that we gain is extremely valuable when we do cross promotions and increase the loyalty of our customers," says Kosiński.

SAS® and Teradata working closely together
The SAS solution runs in close cooperation with a data warehouse from Teradata. The complementary technologies of SAS and Teradata are reinforced by a highly cooperative business relationship between the two companies. "The interoperability and compatibility of SAS and Teradata allows for agile application development, featuring extremely high performance and predictive power in a joint SAS and Teradata environment," says Krzysztof Stępień, Consultant from Sofrecom Poland and Technical Manager of the Churn Prediction Model project. The data warehouse collects data from all major operational systems, including customer relationship management and billing systems, as well as from external suppliers of geographical and market data.

Telekomunikacja Polska uses SAS® Enterprise Miner™ to analyze data from a broad range of sources, gathered by the data warehouse and processed by the churn prediction model application. SAS Enterprise Miner facilitates decision making regarding customer segmentation and identification of customer behavior that is most likely to result in future churn.

For example, data mining analyses have revealed that the risk of churn is significantly higher among customers whose behavior is changing in regard to distribution, structure and dynamics of call number and volume across different time dimensions. Analyses also show that a high churn rate in a customer's geographical or social network neighborhood leads to higher churn of a given customer and leads to further churn propagation.

Immediate access to insight
Speed is a decisive factor when working with customer retention, so Telekomunikacja Polska has designed a highly dynamic infrastructure that enables parallel analysis on two platforms. This speeds up analysis dramatically and gives sales staff immediate access to all relevant analyses.

"SAS and Teradata allow us to merge two completely different analytical requirements and to provide powerful predictive insight for analysts, as well as employees in operational departments. Even though the analyses are extremely complex, they are flexible and fast for our sales people to use. They can bring up all relevant data on screen while talking to a customer," explains Kosiński. "SAS and Teradata are a perfect alliance."

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Copyright © SAS Institute Inc. All Rights Reserved.