modeling

Three inputs beat twelve: activation state, usage recency/depth, and key feature adoption. Start with equal weights. If AUC/ROC against churn is ~0.5, your inputs are wrong, not your math. Fix the signals first.

Health scores work when they are legible and predictive. Keep the inputs few, stable, and behavior-based (e.g., activation milestones met, usage depth/recency, key feature adoption). Write the attribution rules down so you can explain changes. If you can’t predict churn or expansion better than chance, your model is a vanity metric—fix the inputs before tuning…