For the complete documentation index, see llms.txt. This page is also available as Markdown.

How to Identify and Retain Customers at Risk of Cancelling Their Subscription

This guide explains how to use the Subscription Churn score from Batch AI Predict to detect customers likely to cancel their subscription before it ends, and act before it happens.

What Is the Subscription Churn Score?

Batch AI Predict's Subscription Churn score estimates, for each subscriber in your database, the probability that they will cancel their subscription before it reaches its end date. The output is a float between 0 and 1: the closer to 1, the higher the predicted churn risk.

The score is recalculated on a regular basis, so the at-risk population evolves over time as subscriber behaviors change.

Why Use It?

Retention is key for subscription model, because acquiring a new subscriber costs far more than retaining an existing one. By the time a customer has already cancelled, it is too late to act.

With the Subscription Churn score, you can:

  • Detect early cancellation signals before subscribers take action, giving you a window to intervene.

  • Trigger proactive retention campaigns (renewal incentives, value reminders, exclusive offers) precisely when they are most needed.

  • Avoid blanket retention campaigns that erode margin by offering discounts to subscribers who were not at risk in the first place.

How to Use This Score in Batch

1. Orchestration: Automate Retention When Risk Crosses a Threshold (Primary Use)

The recommended setup. Because the score is recalculated regularly, subscribers move in and out of the at-risk population continuously. A trigger-based automation ensures they receive a retention message as soon as they cross your risk threshold.

How to set it up:

  1. Go to Automations in your Batch dashboard.

  2. Create a new automation with an Attribute Change trigger:

    • Trigger condition: Predictive score [Subscription Churn] crosses above [threshold] (the right threshold depends on your business; your CSM can help you calibrate it)

  3. Define your retention message: a personalized email or push highlighting subscription value, a renewal incentive, or an exclusive offer.

  4. Add a capping rule to avoid re-entering the same subscriber too frequently (for example, no more than once every 30 days).

  5. Activate the automation. From that point on, every subscriber who reaches the risk threshold automatically receives your retention message.

Use a Control Group on your automation: exclude a random portion of at-risk subscribers from the retention flow and compare their cancellation rate over 30-90 days against those who received the message. This gives you a clean measure of the retention uplift.

2. Segmentation: Periodic Retention Campaigns

If you prefer to run manual campaigns rather than a continuous automation, you can use the score as a targeting filter on a regular schedule.

How to set it up:

  1. Go to Campaigns in your Batch dashboard and create a new campaign.

  2. In the targeting step, apply a condition based on your configured threshold, for example: Predictive score [Subscription Churn] ≥ 0.7.

  3. Optionally combine with a subscription end date filter to prioritize subscribers whose renewal is coming up soon.

If you run this campaign regularly, save the audience as a named segment (for example, [AI] Churn risk - subscribers) so you can reuse and monitor it over time.

Real-World Use Cases

Industry

Example use case

Streaming & Media

Subscribers whose engagement is dropping: automatically send a curated "you might have missed" digest or a personalized content highlight before their renewal date

Press & Publishing

Subscribers at high churn risk: trigger a loyalty renewal offer (discounted rate, additional month) before they initiate cancellation

SaaS

Users who have stopped logging in: send a personalized re-engagement sequence highlighting features they have not used, triggered as soon as churn risk crosses the threshold

Retail (loyalty programs)

Loyalty members showing disengagement signals: trigger a "your benefits are waiting" reminder or a bonus points offer to reactivate their subscription before renewal


Last updated