Glossary · Business Analytics
Survival Analysis
also: Cox proportional hazards · hazard model · time-to-event
Definition
Survival analysis models time-to-event data — how long until a customer churns, a subscription renews, a machine fails — accounting for censored observations where the event has not yet occurred. Cox proportional hazards is the standard semi-parametric model; deep recurrent survival models handle non-proportional hazards.
Unlike classification models, survival analysis answers 'when will this happen?' and handles right-censoring natively. The hazard function h(t) describes the instantaneous event rate; the survival function S(t) the probability of survival past time t. Cox PH assumes the hazard ratio between groups is constant over time. Deep survival models (DeepSurv, DRSA) relax this assumption and capture complex time-varying covariate effects.
Essays on this concept
- Business Analytics
Survival Analysis for Subscription Businesses: Cox Proportional Hazards vs. Deep Recurrent Models
Binary churn models answer the wrong question. 'Will this user churn?' matters less than 'When will this user churn?' Survival analysis models the timing — and the when determines whether intervention is profitable.
- Marketing Engineering
Customer Lifetime Value as a Control Variable: Re-Engineering Bid Strategies for Profitable Growth
Your bid algorithm optimizes for conversions. But a $50 customer who churns in month one and a $50 customer who stays for three years look identical at the point of acquisition. CLV-based bidding fixes the denominator.
- Business Analytics
Cohort-Based Unit Economics: Why Monthly Snapshots Lie and How to Build a True P&L by Acquisition Cohort
Your company's monthly revenue is growing 20% year-over-year. Your unit economics are deteriorating. Both statements are true simultaneously — and you'll never see the second one in an aggregate P&L.
- Business Analytics
Product-Market Fit Quantified: A Composite Score Using Retention Curves, NPS Decomposition, and Usage Depth
'You'll know product-market fit when you feel it' is advice that has burned through billions in venture capital. Here's a quantitative framework that replaces gut feeling with a composite score — and it starts with retention curves, not surveys.
- Behavioral Economics
Sunk Cost Fallacy in Product Adoption: Why Users Who Customize Retain 4x Longer
Economists call it irrational. Product managers call it retention. The sunk cost fallacy — when properly channeled through customization and effort investment — becomes the most reliable predictor of long-term user engagement.
Related concepts
Authoritative references