Mar 17, 2026 · Updated Oct 22, 2026
Predictive churn prevention: how AI identifies At-Risk customers 90 days before they leave
Quick Navigation
RFM segmentation identifies customers who have already churned. A recency score of 1 means the damage is done, the customer stopped buying months ago, and whatever caused them to leave has had time to solidify into habit. Predictive churn prevention operates upstream of that signal, identifying the customers most likely to churn before their behaviour makes the prediction obvious.
The difference is significant. A customer flagged as at-risk 90 days before their last purchase can be reached with a retention campaign while the relationship is still warm. A customer flagged after 6 months of silence requires a win-back campaign that starts from near-zero engagement, a fundamentally harder and more expensive problem.
What churn actually looks like in B2C data
Churn in B2C businesses rarely happens as a discrete event. Customers do not cancel an account or send a resignation letter. They drift, visit less, spend less, engage less, and eventually stop altogether. The signals are visible in the data before the final exit.
Declining email engagement: A customer who previously opened every message and now opens one in five is not just busy. Their interest is fading. Engagement velocity, the rate at which open and click rates are declining over time, is a stronger churn signal than the current open rate in isolation.
Shrinking basket size: A customer spending €85 per transaction who gradually moves to €40 transactions is signalling a change in relationship. It may be budget-related, or it may be that they are now splitting spend with a competitor. Either way, the trend line matters more than the individual data point.
Channel drift: A customer who shifts from in-store to online to no channel at all follows a predictable disengagement arc. Tracking the channel mix over time, not just the last touchpoint, reveals movement patterns that precede churn.
Reduced visit cadence without an explanatory event: A customer who visits every 10 days and suddenly visits every 25 days has not adopted a new schedule. Something changed in their relationship with the brand.
Churn signal stack, leading indicators ranked by predictive accuracy (90-day horizon):
| Signal | Predictive accuracy (churn within 90 days) | Detection window |
|---|---|---|
| Engagement velocity decline (>40% drop in 4 weeks) | 71% | 8-12 weeks pre-churn |
| Basket size contraction (>30% over 3 purchases) | 64% | 6-10 weeks pre-churn |
| Category narrowing (buying fewer product types) | 58% | 8-14 weeks pre-churn |
| Channel migration (store → online → none) | 67% | 10-16 weeks pre-churn |
| Combined signal (3+ indicators present) | 89% | 6-10 weeks pre-churn |
No single signal predicts churn with high confidence. The predictive power comes from combining signals, a customer showing 3 or more indicators simultaneously has an 89% probability of churning within 90 days.
The intervention window and what to do with it
Detecting a at-risk customer 90 days before their probable last purchase creates a window for intervention. What happens in that window determines whether the customer is retained.
Weeks 1-4 after detection: The intervention should feel like a natural touchpoint, not a retention alarm. An SMS referencing something specific about the customer’s history, not a generic re-engagement offer, is the right tone. “We noticed we haven’t seen you since the autumn collection, the new arrivals this week have a few pieces that match what you loved last time.” The customer does not know they were flagged as at-risk. They receive what feels like a thoughtful personal message.
Weeks 5-8: If no engagement from the first message, escalate the specificity. A message from a named person on the team (the manager, the personal shopper, the account manager, whoever is relevant) that is even more specific: “I wanted to reach out personally, is there anything we could do better for you?” This works because it invites a response rather than demanding a purchase.
Weeks 9-12: The final intervention window. If the previous two touchpoints produced no engagement, this is the moment for a meaningful value offer, not a promotional discount, but a genuine reason to return: an exclusive event, early access to something specific to their history, or a personal invitation that treats the non-response as an oversight rather than a rejection.
Predictive churn intervention, recovery rate by intervention timing and approach:
| Intervention approach | Recovery rate | Average revenue protected per customer | Cost per recovery |
|---|---|---|---|
| No intervention (discover at churn) | - | €0 | - |
| Reactive win-back (post-churn) | 14% | €180 | €42 |
| Early detection, generic offer | 28% | €340 | €38 |
| Early detection, personalised message (no offer) | 41% | €490 | €22 |
| Early detection, personalised + escalation sequence | 58% | €620 | €19 |
Personalised early intervention without a discount offer recovers customers at 3× the rate of post-churn win-back campaigns, and at lower cost, because it does not require margin-eroding promotions to work.
Automating the detection and response
In Caramel, the churn signals (time since last purchase, falling visit frequency, emails no longer opened) live as traits on each customer record, and an at-risk audience updates itself as customers cross the threshold. A journey starts the right intervention for each customer’s segment and channel preference, and campaign reports show how many at-risk customers came back.
For the RFM foundation that powers churn segment identification, see The RFM Model Every B2C Business Should Build Before Running Another Campaign. For lifecycle trigger campaigns that fire automatically on churn signals, see Trigger-Based Marketing: The 7 Customer Signals That Should Launch Automatic Campaigns.
Every attendee who leaves without a reason to come back is next year’s ticket sale left to chance. Caramel brings attendees back without a marketing hire: keep your CRM (HubSpot and Bitrix24 connect directly), start from campaigns and forms built for your trade, and let AI write the first draft. Plans start at €49 a month, you send through your own email or SMS provider at its own rates, and there’s a 14-day money-back guarantee.
Quick Navigation
Get in Touch
Have questions about implementing these strategies? Let's discuss how Caramel can help your business.
Related Blogs
See All Blog
Caramel vs Mailmodo: when interactive emails are not enough
The tool you choose should bring more of your existing customers back, at a cost that doesn't grow faster than your business. Mailmodo and C
Personalisation at scale: how AI delivers 1-to-1 marketing without 1-to-1 human effort
Personalisation is the word the marketing industry has used for fifteen years to describe everything from inserting a first name into an ema
Compliance by design: capturing KYC, AML and consent information from international buyers
The international deal that falls apart at the last minute often fails on paperwork: the source of funds can't be documented in time, an ide
Turn customer data into the next conversation
Keep your CRM; there is nothing to migrate. AI drafts the first version, so you don't need to hire a marketer. Plans start at €49/mo with a 14-day money-back guarantee, no questions asked.


