Built Models → +£1.1M ARR From Churn Model: Data Science Bullets

Free · No signup · Recruiter-reviewed

Three vague nouns ('predictive models', 'customer outcomes', 'business strategy') replaced with the algorithm class, AUC, the operational workflow it landed in, the save-rate delta, and the £ARR attribution. Data scientists who can quote ARR attribution outrank those who only quote AUC.

Deployed a gradient-boosted churn-risk model (AUC 0.87) into the renewal workflow, lifting save-rate 23% → 31% and adding £1.1M ARR over 4 quarters.

What changed and why

  • Always tie the model to a £ outcome. Save-rate alone is operational; £1.1M ARR is the C-suite outcome.
  • Quote AUC, precision/recall, or RMSE — pick the one that matched your loss function. Without it, model claims read as resume fluff.
  • Name the deployment surface (renewal workflow, inbox routing, fraud queue) — proves the model shipped, not just trained.
  • Window (4 quarters) prevents 'attribution lasted 2 weeks' assumption — recruiters now grade attribution windows.

Recruiter perspective

“AUC 0.87, save-rate delta, £1.1M ARR tied — this data scientist owns business outcomes, not Kaggle scores.”

— VP Data Science · Subscription SaaS

Related rewrites