Refund Abuse labelling uses a tags‑first approach. This gives teams the flexibility to express granular, policy‑aligned behaviours and capture specific fraud contexts more effectively than binary labels.
There are two main reasons why using tags can be beneficial:
Tags can act as a proactive defense against refund abuse, enabling the use of Ravelin’s rule engine and Connect network to prevent abuse as it happens.
Precise tags can be used to refine the model, enhancing its ability to distinguish between genuine customers, potential refund abusers, opportunists and return fraudsters, ultimately improving predictive accuracy.
Tip: Keep your tag set focused and documented. If you need help defining a tag taxonomy, see “Need help?” below.
Adding a tag on a customer currently has no direct impact on future orders placed or refunds requested by that customer. To influence future actions based on these tags, you must set up a rule in the Ravelin dashboard at the relevant checkpoint.
For example, you might prevent known refund abusers from making purchases at the checkout checkpoint or automatically approve refunds for trusted customers at the refund request checkpoint.
We have removed the “Refund Abuse type” manual review option from the dashboard and API. Previously, reviewers could select binary labels such as “Refund Abuse” or “Not Refund Abuse.” This workflow is now deprecated in favour of tags to provide richer, client‑specific semantics. If you previously relied on manual review endpoints, please transition to using tags.
Mapping your existing labels to tags? Contact your Account Manager for support on taxonomy design and rule automation.
Test your refund abuse integration
Was this page helpful?