QA: What are your experiences with survival analysis?

By: Bart Baesens, Seppe vanden Broucke

This QA first appeared in Data Science Briefings, the DataMiningApps newsletter as a “Free Tweet Consulting Experience” — where we answer a data science or analytics question of 140 characters maximum. Also want to submit your question? Just Tweet us @DataMiningApps. Want to remain anonymous? Then send us a direct message and we’ll keep all your details private. Subscribe now for free if you want to be the first to receive our articles and stay up to data on data science news, or follow us @DataMiningApps.

You asked: What are your experiences with survival analysis?

Our answer:


We’re big fans of survival analysis, though we do believe you should approach it with care.It’s been quite popular in insurance analytics and becoming mainstream in credit risk modeling as well (both for PD as well as LGD modeling).In other application fields, e.g. marketing analytics, it’s less widely used.The thing with survival analysis is that it’s quite complicated to build, evaluate and implement those models. If you are a rookie to the field, I would recommend starting off with a simple (logistic) regression modelwith a fixed time horizon first. Once you have that up in the air, you can start thinking about survival analysis as your next step. As in classical analytics, start by doing some descriptive analysis first using e.g. Kaplan Meier analysis.

The next step is then to build predictive models using e.g. parametric survival analysis or proportional hazards regression. If you are a real modeling freak and up for a challenge, you can experiment with spline based methods as well. We found those to perform particularly well in both credit risk modeling and churn prediction, although as always, the price you pay for this is a complex to understand non-linear model.

P.S.: Don’t forget to submit your suggestions for questions!