AnalyticBridge
A Data Science Central Community
Churn modeling using Survival analysis
Hi,
I am trying to build a churn model using survival analysis for our top tier customers. The thing is that we are not a subscribtion based company, which makes the defintion of churn/defection hard to define. I can try to define a churn customer as a customer whose annual spent with us drops by 10% or 20%. However, what is the OPTIMAL way of defining a churn customer? Is it a business decision that each company has to make or can it be formulated as an optimization problem and be solved using true optimization techniques? Thanks.
Replies to This Discussion
-
Permalink Reply by Jeff on
-
My 2 cents:
I have faced this problem utilizing survival analysis itself -- at some point in time since last purchase, when does the probability of purchase dip below a business rule (say 10%). I would then deem the customer attrited.
Second, I have tested an intervention (a discount offer) at various times since last purchase and measured where the incremental lift versus a control group was the highest. Then shape of the smoothed curve can help inform about organic demand...
Love to hear others opinions.
© 2021 TechTarget, Inc.
Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
