Decisions · Layer 1
Should you use a taxonomy for loyalty fraud
Use a fraud taxonomy that separates account, claim, issuance, redemption, collusion, and insider events. Route each class to the control that can observe it.
Use a fraud taxonomy that separates account, claim, issuance, redemption, collusion, and insider events. Route each class to the control that can observe it.
## The decision boundary Fraud is an outcome category, not a single signal. Account compromise, false claims, issuance abuse, redemption abuse, collusion, and insider abuse require different evidence.
## The options
### Event taxonomy Choose this when controls and owners differ by event. The cost is additional operating complexity.
### Risk score Choose this when many signals need triage. The cost is more measurement and exception handling.
### Manual case classes Choose this when volume is low and evidence needs judgement. The cost is a stronger funding and review obligation.
## What it costs you The currency is liability, margin, engineering time, operating capacity, or member trust. In a hypothetical illustration, 2 points per dollar on 400 dollars of spend creates 800 points. At a hypothetical 1 cent value, that is 8 dollars of liability. Ten comparable cases therefore represent 80 dollars of stated value.
## How to decide 1. Name the behaviour or obligation the rule must control. 2. Identify the independent evidence that proves the event. 3. Price the member, operating, and liability cost of each option. 4. Choose the least complex control that protects the least reversible outcome. 5. Set the evidence that would cause a later review.
## What breaks The failure mode is a rule that measures its own success. Keep source evidence, eligibility, issuance, adjustment, and fulfilment separately observable. Revisit the recommendation when the balance has no meaningful value or the event cannot be independently verified.