Repurchase Prediction model
Predicting which customers are statistically overdue for their next purchase.
What is the Repurchase Prediction model?
While the Propensity to Buy model gives a general 30-day purchase probability, the Repurchase Prediction model specifically identifies customers who are statistically overdue based on their personal purchase rhythm.
A customer with a 0.82 repurchase score and who hasn't bought in 45 days (when their average gap is 38 days) is a strong candidate for a gentle nudge — they intend to buy again, they just need a reminder.
Repurchase score vs. win-back window
- High repurchase score → Customer is likely to buy again — they just need a nudge at the right time
- Win-back window open → The right time is now — receptivity is at its peak
- Both → Highest-priority target: a customer who wants to buy and is currently receptive
Learn more: Purchase prediction
Related in Intelligence Models
All 12 articles →Win-back Timing modelHow LiftSignals identifies the optimal day to re-engage a lapsed customer — and why timing is everything.1 min readPropensity to Buy modelHow LiftSignals scores the probability of a customer making a purchase in the next 30 days.1 min readHow the intelligence models workAn overview of LiftSignals' signal models — how they train, how accurate they are, and when to trust them.2 min readChurn Detection modelHow the churn score is calculated, what the risk bands mean, and how to act on them.2 min read
Still stuck?
Write to support@liftsignals.com — a human answers within four business hours.