This guide explains how to use the Product Propensity score from Batch AI Predict. Stop sending product campaigns to your entire database. Reach only the customers who are genuinely interested.
Batch AI Predict's Product Propensity score predicts, for each customer in your database, their likelihood to purchase within the upcoming days inside a specific and predefined product, category, or brand target. The output is a float between 0 and 1: the closer to 1, the stronger the predicted propensity.
This score is configurable: you define the product target you want to focus on with your CSM, and Batch AI Predict builds a dedicated scoring model for it. Each configuration generates a distinct attribute on the customer profile.
Product Propensity vs. Product Recommendation: which one do you need?
Product Propensity → You have a campaign on a specific product or category and want to find the best customers to target. Use this for segmentation: "Who should I contact for this campaign?"
Product Recommendation → You want to find the best products to show to every customer. Use this for personalization: "Which products should I put in this customer's template?"
Most product campaigns go out to the full database by default. The result: low relevance, high unsubscribe rates, and wasted budget on customers who have no interest in what you are promoting.
With the Product Propensity score, you can:
Reduce your campaign volume by targeting only high-propensity profiles.
Increase your click and conversion rates by reaching more receptive audiences.
Protect your CRM pressure and reduce opt-out risk across the rest of your base.
The core use case: use the score as a targeting filter directly in your campaign. You start from a product or category and identify the best audience to reach.
How to set it up:
Create your campaign in Batch.
In the targeting step, apply a condition based on your Product Propensity score: Predictive score [Score name] ≥ X
Choosing your threshold: Batch recommends a default threshold that balances revenue impact and engagement quality. You can adjust it based on your campaign objective: a lower threshold increases your reach for broader revenue impact; a higher threshold targets only the most receptive profiles for better engagement rates. Your CSM can help you calibrate this.
If you plan to reuse this audience across multiple campaigns or want to monitor how it evolves over time, you can save it as a named segment: for example, [AI] High propensity - [Category name].
You can combine the propensity score with other targeting criteria (recency, loyalty tier, last purchase date) to further refine your audience.
Recommended test: Run an A/B/C Targeting Comparison Test to compare the Batch AI Predict targeting against your existing business rules (e.g., "customers who purchased in this category in the last 6 months"). See the Performance Measurement Guide for details.
Once you are comfortable with one-shot segmentation, you can take it a step further: use the score as an entry condition in an automation, so the right customers are reached automatically. For example, as soon as a customer's propensity crosses your threshold, regardless of any campaign launch.
Example setup:
Automation entry condition: attribute change trigger on Predictive score [Score name] crossing your threshold
Action: send a targeted message to customers the moment they become high-propensity; no manual segment refresh needed
Result: no high-potential profile is missed between two score recalculations
This pattern works well for always-on automations (e.g. a standing campaign for a category or brand) rather than one-shot sends; the automation runs continuously and catches each new high-propensity customer as they appear.
Industry
Example use case
Retail
Seasonal promo (coats for winter, etc.): instead of blasting the full database, target only customers with high propensity for the relevant category; reducing volume while improving conversion rates
Media & Entertainment
New series release: reach only subscribers with propensity for the relevant genre (action, documentary, etc.) and protect the rest of your base from irrelevant pressure
Travel
Always-on automation: use an attribute change trigger to automatically notify travelers the moment their propensity for in-destination activities crosses the threshold; no manual refresh needed
Last updated
