Teradata helps carriers keep a leash on customers

With the battle to retain customers in the telecommunications market apparently fiercer than ever – especially in the wireless arena the thought of losing a customer to the competition can make even the most resilient executive’s stomach churn.

To keep telco execs healthy and employed,Teradata, a division of NCR Corp., unveiled a new tool called Survival Analysis Software. It’s designed to help carriers retain customers.

“It’s really based upon a statistical methodology that was first used by the medical community,” said Judy Bayer, spokesperson for Teradata in London. “It’s called survival analysis because it was designed to predict how long patients would live.”

Bayer said survival analysis programs predict how long it will take for an event to occur – in the case of telecommunications, how long before a customer moves on to another service provider or product, a phenomenon known as “churn.”

Survival analysis looks for similarities between past churners and customers that exhibit “risky behaviour,” such as late payments, frequent complaints about service and decreased use of service.

Bayer said the tool scores each customer based on variables that indicate risky behaviour, and the score is automatically updated in tandem with the customer’s actions.

Teradata says the system works best when connected to Customer Relationship Management (CRM) software, which tells the carrier what to do about potential churners. Marketing or sales could be notified to offer the client new services, for example.

According to David Hawley, analyst with The Yankee Group in Boston, Teradata faces stiff competition from companies such as SAS Institute Inc., the market leader, and SPSS Inc.

“Every [major] wireless operator in North America is currently using some sort of analytics platform to predict churn,” he said.

Teradata could have a hard go of selling Survival Analysis in Canada, judging by the success that wireless carriers in this country have with systems already in place.

For instance, Telus Mobility has a churn management platform built on technology from SAS and Informatica Corp. The system helped keep the carrier’s churn rate at a low 1.68 per cent last year, meaning less than two per cent of Telus Mobility’s customers went searching for greener pastures, said Mark Langton, Toronto-based spokesperson for Telus Mobility.

Meanwhile, Rogers AT&T Wireless relies on SAS’s Statistical Analysis solution to predict churn. The carrier has 3.7 million customers and its churn rate was just 1.98 per cent in 2002, said Raj Doshi, vice-president of customer base management with Rogers AT&T Wireless in Toronto.

Doshi said predicting churn involves data capture, statistical scrutiny and action based on CRM information. He said statistical analysis tools such as Teradata’s Survival Analysis can only do so much. The key to developing an effective prediction system involves creating models of risky client behaviour.

Hawley agreed. “It’s more about…the way that you model the data than the analytics itself,” he said.

Survival Analysis is priced according to implementation. For more information, see the company’s Web site, www.teradata.com.

Related Download
The Landscape of Self Service Analytics Sponsor: IBM
The Landscape of Self Service Analytics
Download this report to examine the current state of self-service analytics across all industries and company sizes, and view the technology decisions and analytical performance of organizations that reported high levels of self-service in their analytical use base.
Register Now