easy site maker

Predicting Churn

American Express 

American Express began looking for indicators that could really predict loyalty and developed sophisticated predictive models to analyze historical transactions and 115 variables to forecast potential churn. 

Amex wanted to shift their traditional approach to business intelligence of hindsight reporting and trailing indicators to a prediction model that would indicate how loyal their customer base was, now and in the future. By developing a new approach, looking in depth at spend analysis, our sophisticated predictive model analyses trillions of historical transactions, using over 100 variable factors to forecast potential churn. In the Australian market alone, they now believe they can identify 24% of accounts that will close within four months.

  1. SQL Server Based Technology - no special skills or training required. Microsofts SQL Server is a well known and understood technology throughout the business world.
  2. Cross Department Insights - Using these new algorythms and methodology, Amex are not only able to predict churn, but are now appliying the same techniques to identifying and preventing fraud.
  3. Unique Approach - The ability to use existing data in new and innovative ways, has meant that Amex can focus resource where it is most productive, and concentrate on developing informed strategies that allow them to grow the business intelligently.

See how Global Pacific can help your business


Suite 997 Trevisome Business Park, Truro, Cornwall,
England TR4 8UN


Email: support@gpc.com 
Phone: +44 (0) 20 7100 7835 
Phone: +1  917 259 1094