In the context of financial crime compliance, the term “true positives” refers to instances where a system or process correctly identifies suspicious activity or behaviour as a legitimate threat or violation. For example, when an Anti-Money Laundering (AML) system flags a transaction for review, and upon investigation, it is confirmed that the transaction is indeed linked to illicit activity, this is considered a true positive. 

True positives are critical in financial crime compliance because they represent accurate detection of threats, allowing compliance teams to take appropriate action. However, achieving a high rate of true positives can be challenging, as systems must balance between detecting real risks and avoiding false positives (incorrect alerts). By improving true positive rates through advanced technologies like AI, compliance teams can focus their efforts on genuine threats, making their operations more efficient and effective.