Another way to do this is based on a paper by Fader & Hardie [0] that uses a probabilistic model, instead of a regression-based one. It's highly readable, and very intuitive. The technique workss particularly well when there's only limited cohort data (e.g. early days of a startup) and you can't just blend years of prior cohort data. A former colleague and I made a web-based implementation as a little weekend project if anyone wants to try it out: <a href="http://retentionizer.herokuapp.com" rel="nofollow">http://retentionizer.herokuapp.com</a><p>[0] <a href="https://marketing.wharton.upenn.edu/files/?whdmsaction=public:main.file&fileID=341" rel="nofollow">https://marketing.wharton.upenn.edu/files/?whdmsaction=publi...</a>