Is Your New Year’s Resolution to Lose $£€ through Increased Customer Churn? Mine Sure Isn’t!

Learn how combining propensity scoring with cluster analysis ensures strong growth

Franco PrimavesiJanuary 25, 2017

Download White Paper

Companies like to have high numbers in their revenue column and telecommunications providers are no different. But how do you ensure strong growth and profit year over year?

The answer is combining propensity scoring with cluster analysis.

In the telecom industry, it is critical to reduce attrition and prevent contractual customers from switching to a competitor. Customer churn can impact revenue and profitability down the line, and we all know, it is much more cost effective to retain a customer than onboard a new one. With a combination of propensity scoring and cluster analysis, telecom organizations can predict their attrition rate, identify which customers will churn, and put solutions in place that will reduce customer turnover and shore up your bottom line. Let’s start with propensity scoring.

Propensity Scoring

Propensity scoring combines business data with advanced analytics results to predict a customer’s propensity to churn. Propensity scoring gives telecom providers real-time insight into customer activity. Tracking valuable customer information, like balances or daily mobile usage, and understanding customers’ real-time activity, presents tremendous revenue generation opportunities to gain maximum profit, address churn risk and retain customers.

By combining data throughout the customer lifecycle from acquisition, onboarding, retention, and loyalty efforts, telecom companies can identify churn patterns and drivers further impacting turnover.

Once telecom providers have identified at-risk customers, they can use cluster analysis to prioritize the list of at-risk customers and take a deeper dive into the reasons a customer might cancel their service.

Cluster Analysis

Cluster analysis complements propensity scoring. It allows telecom providers to group subscribers into “clusters” to identify subgroups within a larger group using advanced analytics. By doing this, telecom companies can better identify subscribers with similar drivers and churn triggers, allowing them to develop and implement focused strategies that proactively increase subscriber retention and, ultimately, the bottom line.

Furthermore, by using advanced analytics, telecom providers can better identify subscribers worth retaining. For example, some subscribers may be on the verge of churning because they simply cannot afford to pay their bill. In a cluster analysis, this would be identified as one sub group. However, another cluster may be subscribers likely to churn because they are unhappy with customer service.  By categorizing or clustering these drivers into groups, telecoms can identify opportunities for improvement, more effectively prioritize which clusters are worth rescuing and which clusters are going to churn despite efforts to avoid such an outcome.

This type of analysis allows companies to focus their attention on the right promotions, service offerings and ways to fix their service for the right subscribers, rather than making improvements for the wrong subscribers.

So how do you ensure the advanced analytics data can help reduce churn rates, attract the right subscribers and contain accurate behavior, demographic and subscriber data? Simple, by implementing an Enterprise Data Analysis platform that combines propensity scoring with cluster analysis to pinpoint analysis and subsequent actions to cost effectively reduce churn.

The Solution

With an Enterprise Data Analysis platform, advanced analytics combines different sets of tools to provide comprehensive coverage of the customer lifecycle and identifies if and why a customer may churn. The platform looks at a combination of past, present and future data to target the reasons a customer may leave, through prescriptive analytics, usage and behavioral analytics, identity analytics and operational analytics, to be combined as required to precisely address any problems a customer is having at hand.

In-house data sets such as historical customer data, as well as a rich collection of third-party datasets such as economic, demographic and Social Security among others, are incorporated into the advanced analytics. The advanced analytics then produce accurate, actionable outcomes and deliver valuable insights into customer behavior and use that data to reduce customer turnover.

With an Enterprise Data Analysis platform, telecom providers can successfully retain customers who exhibit the highest propensity to be rescued. In addition, it can save valuable time and money by avoiding low ROI initiatives targeted at the wrong type of customer.

To learn more about cluster analysis and advanced analytics, download this white paper:

Get Insights

For a deeper dive into this topic, visit our resource center, where you will find a broad selection of content that represents the compiled wisdom, experience, and advice of our seasoned data experts and thought leaders.

Download White Paper