|Lessons Iin Loyalty|
Churn modeling is very much like gourmet cooking. When done well, it has a lot of science, a dash of finesse and even a pinch of intuition. With rates of customer defection reaching epidemic levels in industries like retail, travel, healthcare, and banking, predicting turnover has become significantly more important to business in recent years. Having reviewed material on many churn models across a multitude of industries, we've concluded that perhaps no industries practice more predictive modeling than telecom and financial services. This makes sense because of their high degree of customer risk and defection.
Predictive churn modeling techniques vary in degrees of complexity. Take a simple example, like Wachovia Bank, headquartered in Charlotte, N.C. Wachovia looks at demographics, life events (divorce, losing jobs, opening a business, graduating kids, etc.), declines in account balance levels, and the
A couple of years ago, I interviewed Professor Adrian Payne, of the Cranfield University School of Management in the U.K. Payne is perhaps the planet's most knowledgeable academic on the subject of retention and turnover modeling. Professor Payne explained that, in his view, companies first have to look at the cost of acquisition, then build in retention spending, and other costs such as upsell and cross-sell. He's seen segments being built around behavioral-based market research (similar to what the banks are doing), eventually getting down to a microsegment level.
He also opines that few companies have sufficient customer information to develop really accurate models and that companies should also look at factors such as competitive intensity, the industry retention average, over performance and under performance on service, etc.
Nevertheless, there are several professional firms that stand out in their approaches to modeling. SLP InfoWare, based in France, has a model (called Churn/CPS) which tracks multiple end-user defined churn behaviors, so that clients can engage and refine their retention strategies.
SLP InfoWare clients are almost exclusively in the telecom industry. One of them, Cellular One of Puerto Rico, equips customer service agents with predicted at-risk customer behaviors, so they can apply any of several potential marketing approaches to reduce churn. Using software provided by SLP InfoWare, Cellular One calls customers who have been identified as likely to be delinquent. The agents, in another example, can offer more economical plans to customers identified as potentially considering other providers. The software also gives agents the opportunity to upsell and cross-sell customers. Retention management at Cellular One feels the agents do a better job because, by using the software results, agents know more about customer behavior.
Using the Churn/CPS model, they've been able to reduce customer turnover by one-third. Since telecom churn averages about 30% in the U.S. and Europe, and more than 50% in the Asia-Pacific region, this is really significant. SLP figures that, with their model, something like 62% of churn behavior can be modified if spotted in advance, so this offers clients a fair amount of flexibility in how they approach at-risk customers.
A second noted modeling firm is U.K-based Quadstone. Quadstone positions itself as a holistic predictor of customer behavior; and, through their Decisionhouse software, they offer marketers the opportunity to profile and segment customers ?both visually and interactively.? Like SLP InfoWare, they have taken complex statistics and mathematical algorithms and converted them to hands-on application for marketers. They take customer data from multiple channels (call records, call center logs, retail network data, information from various databases, etc.) and create predictive models and programs that help marketers influence the at-risk customer to stay or encourage the active customer to purchase additional products and services.
In the telecom industry, they estimate they've been able to double response rates to add-on service campaigns, reduce customer churn by more than 10% and reduce the costs of churn management by over half. They do this by optimizing value at every customer touch point and by better understanding and predicting behavior.
The third innovative churn modeling consultant is @RISK, Inc., based in Pennsylvania. @RISK, Inc. uses advanced techniques -- neural network protocols, artificial intelligence and causal inference algorithms -- to detect patterns and trends in customers' transactions which could mark them as potential defectors. Their Pathfinder program 'learns' the stable, causally associated indicators of defection from the transaction data itself, yielding better predictive accuracy and precision. This, in conjunction with systems that can produce unique prediction equations at the microsegment level, have enabled @RISK, Inc. to identify the vast majority of "would-be" defectors months in advance. @RISK Inc.'s clients include fund companies, brokerage firms and banks, and they have used Pathfinder to help identify high-risk customers and alternative positioning approaches. @RISK, Inc.'s techniques have proven both leading-edge and highly effective.
One business writer, commenting on the emergence of churn prediction in the fund industry, said: "As this technology advances, the marketing departments of fund companies will start to look decidedly different. You may be hiring segment managers rather than product managers into your marketing group. And sooner than you think."
This opinion can apply to any industry and business where excessive defection is a concern. In other words, marketing will be seeking the gourmet chefs -- the Emeril Lagasse's -- of the predictive churn modeling world, to help create the most appetizing loyalty menus for their customers.
Michael Lowenstein is managing Director of Customer Retention Associates, a customer and staff loyalty program development, research and consulting firm located in Collingswood, N.J. He has three decades of experience in customer and staff loyalty research and has written several books, including Customer Retention: Keeping Your Best Customers, The Customer Loyalty Pyramid and Customer Win-back: How To Recapture Lost Customers - And Keep Them Loyal.
Have a question about predictive churn modeling or customer loyalty tactics? Ask Michael now.