Case Study: EDF Energy achieves reduced customer churn and significant savings with SAS predictive analytics

EDF Energy analyzes its customer base to build its marketing strategy

EDF Energy, operating in the highly competitive UK retail energy market where the average switching rate is about 38%, needed to understand and reduce customer churn. Its Customer Insight team had to analyze very large data volumes (hundreds of millions of rows and some 400 variables) and uncover the behavioral and demographic drivers that predict which customers were likely to defect.

EDF implemented a SAS data access, management and predictive‑analytics platform to build churn and propensity models, enriching internal records with third‑party attitudinal and lifestyle data. The models flagged high‑value segments—showing the top 25% were four times more likely to take dual fuel and far less likely to leave—enabling targeted communications, more efficient upgrade offers and reduced wasted marketing spend, delivering measurable cost savings from even small improvements in retention.

EDF Energy

Clifford Budge

Customer Insight Manager