The task
Triage one transaction-monitoring alert against the customer’s KYC file and twelve months of account history. Close it, or escalate it for a suspicious-activity filing with a written narrative.
Proposed by PIG-DemoRank 4 of 12In the first set
Financial-Crime Alert Triage
Who it is for
BSA / AML Officer
Almost every alert my team reads is a false positive. The handful that are not is the entire conversation with my regulator.
The reward
Pays for closing false positives, in analyst hours per thousand alerts. That is the number the operating budget is built on.
The counterweight
A missed escalation on an alert that later became a filed report costs more than every hour saved that month. The asymmetry lives in the reward weights, where you can read it and argue with it, instead of in a policy memo.
The counterweight is the part worth arguing about. A reward with nothing pulling against it is a target, and a target is what a model learns to hit instead of doing the job.
What exists today
Nothing. There is no environment for this vertical, no recorded run, and no number. It is a proposal, written to the same shape as the one that is built so you can judge it on the same terms.
The environment that does exist is Word Five. It is a word game, and it is deliberately not one of these twelve: it is there to show the machinery, not to imply we have built yours.