Two weeks of warning before a user goes quiet.
Churn Predictor learns what leaving looks like in your product and flags the users heading that way, while there is still time to win them back.
| User | Risk | Top signals |
|---|---|---|
| u_48211 | 86% | No order in 19 days, 3 failed coupons |
| u_30977 | 79% | Sessions down 70% week on week |
| u_51203 | 72% | Uninstalled push, cart left twice |
| u_12840 | 64% | Only opens on weekends now |
| u_77310 | 58% | Support ticket unresolved 6 days |
A fresh list every morning
Each day, Zortilla scores active users on how likely they are to stop using the product in the next 14 days, based on your own history of who left.
- Trained on your data only, so it learns what churn looks like in your product.
- You define leaving: no session, no order, or a cancelled subscription.
| User | Risk | Top signals |
|---|---|---|
| u_48211 | 86% | No order in 19 days, 3 failed coupons |
| u_30977 | 79% | Sessions down 70% week on week |
| u_51203 | 72% | Uninstalled push, cart left twice |
| u_12840 | 64% | Only opens on weekends now |
| u_77310 | 58% | Support ticket unresolved 6 days |
Every prediction shows its reasons
See the signals that pushed each user's risk up or down: fewer sessions, failed payments, features abandoned, support issues. Scores are labeled as estimates.
Points added to the risk score by each signal. Model refreshed 2 hours ago.
Send at-risk users to your messaging tool
Sync the list to Braze, Customer.io, HubSpot or a webhook, or download a CSV. Users move in and out of the audience automatically as their risk changes.
Model accuracy shown
See how well last month's predictions matched who actually left.
Refreshed daily
Scores update every 24 hours, or hourly on Scale.
Estimates, labeled
Predictions are always marked as estimates with the data behind them.
Common questions
How much data does it need?
Which plans include it?
You made it to the bottom. Now let's get your users here.
Every page you scrolled past was a step in a funnel. Install Zortilla and see the same picture for your own product, with the reasons people leave at each step.