I am exploring churn and lifetime modeling. From what I see on various online material, the lifetime period is defined as 1 / churn-risk.

For example, if the churn risk for a 12-month period is estimated to be .3, the lifetime is calculated to 3.3 years by 1 / .3.

Is there a mathematical proof of this way of modeling the lifetime period? Intuitively, 1 - churn risk sounds more correct (probability of not churning).

Where does the assumption that churn risk increase over time come from? Is there a distribution formula that is derived to 1 / churn risk?


This comes from the geometric distribution. If the probability of churning in any given year is $p$ (where $p$ is constant across years, and years are independent) then the expected number of years until you churn is $1/p$.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.