Polish wireless provider taps into big savings with SAS®

With SAS® Analytics, Poland’s Polkomtel reduced its credit-scoring IT expenses by 90 percent, speeded the approval process for new customers and fine-tuned collection operations to encourage loyalty. The net result: a threefold decrease in bad debt and churn.

The Polish wireless market is saturated, with nearly the entire adult populace signed with a wireless carrier. Polkomtel has 14 million of those customers – about one-third of the market. "The environment is very competitive,'' says Jacek Szustkowski, Director of the Activation and Collections Department. "It's hard to compete for new customers.'' What Polkomtel doesn't want to do is extend service to customers who can't or won't pay, nor does it want to turn off loyal customers with overly harsh collection tactics. At the same time, it must work more efficiently as regulators have recently slashed the fee charged by operators for each call answered by a cell phone.

The company has an additional hurdle: Poland is only now establishing a credit bureau and strict government privacy regulations prohibit businesses from asking certain questions or seeking data on customers elsewhere. "It's a very complex situation,'' Szustkowski says.

The integrated credit scoring system from SAS is a powerful tool that gives us an edge on our competition.

Jacek Szustkowski
Director, Activation and Collections

Staying competitive in a saturated market

"When we offer service through a postpaid account it's like a loan, but unlike a bank we must be very fast in deciding who can get service,'' Szustkowski said. And if the "borrower" doesn't pay, the company faces an additional quandary. Rapidly moving to cut off the customer increases churn and the risk that the debt will never be collected. It's difficult to ascertain which customers will pay up and which will continue to ring up bad debt. "We do want customers to stay and pay another bill,'' Szustkowski says.

Szustkowski's team tried building scoring models to screen new customers and segment late payers, but before using SAS the process was difficult. "We implemented some scoring models but they weren't flexible. They took a long time to implement, the analysis was very complicated and we had no tools to evaluate their effectiveness," Szustkowski said.

Polkomtel chose SAS because the solution offered flexibility and could be implemented quickly. The company was already using SAS Analytics successfully for direct marketing and segmentation, and Polkomtel uses SAS partner Teradata for its data warehouse. With SAS, Polkomtel has build 13 active models (compared to one previously). Each model takes about one month to build compared to eight months for previous efforts – shaving 90 percent off the cost of model building.

Some of the models feed an online solution that helps the person selling the service assess a customer's creditworthiness within three seconds and offer the appropriate service. Marketers can create campaigns that appeal to the kind of customer who stays and pays their bills. And Szustkowski's collection staff can target its dollars at the right customers. Some customers just need a text message reminder to pay a bill – a cheap solution that keeps the customer happy. The scoring solution helps Szustkowski's staff pick out customers who need more expensive interventions. The collections staff even knows what time of day is best to reach a customer thanks to a "contactability score" Polkomtel built with SAS Analytics.

"Collections is not something received positively by customers,'' Szustkowski says. "With SAS, we've improved our collection efficiency while also increasing customer satisfaction. And our reputation with the sales force has changed. We used to be the conservative group that kept them from signing up customers. Now we can talk with numbers and trends and help sales plan promotions that will bring in the right customers. And we've given them an automated process that eliminates a time-consuming manual one.''

"Our progress in bad debt reduction is significant, the return on investment is very fast,'' Szustkowski says. "The integrated credit scoring system from SAS is a powerful tool that gives us an edge on our competition.''

Współpraca SAS i Polkomtel


Reduce bad debt, decrease churn and quickly determine the creditworthiness of new customers


  • SAS Analytics


Reduced IT costs for modeling by 90 percent, increased model production from one to 13 models, significantly reduced bad debt and churn, increased customer satisfaction with debt-collection process

Visit Polkomtel on the Web (Polish only)

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.