Pacific Gas & Electric (PG&E) needed to identify customers at risk of leaving their service. Churn analyses tailored to the utility industry leveraged customer addresses, gas consumption patterns, product preferences, and contract terms, unveiling a 69.93% likelihood of customer attrition for the at-risk segment.
The decision behind the question
Pacific Gas & Electric needed to know which customers were about to leave its service, and why, early enough for retention outreach to matter.
Data and methods used
Customer addresses, gas consumption patterns, product preferences, and contract terms were joined into a churn model tuned to utility data, with time-to-event analysis estimating not just who would leave but when.
What the analysis found
- •The at-risk segment carried a 69.93% likelihood of attrition, well above the portfolio baseline.
- •Consumption change over the preceding billing periods predicted departure more sharply than contract age.
- •Timing clustered around specific contract milestones, giving a usable outreach window.
What changed as a result
Retention contact was scheduled against the predicted timing rather than sent as a single campaign, concentrating effort on the accounts and weeks where it could still change the outcome.
Related work is grouped under Market Research, and the methods used here are described in more detail under analytical capabilities.
Other Averisys Analytics studies related to Customer Churn
Each study documents the question, the data, the method, and what the finding made possible. Select any title to read the full write-up.
Trusted by leading organizations
Averisys Analytics guarantees its security.
