Adaptive Workflow Allocation in Human–Machine Cooperative Anti-Money Laundering Operations

This study develops an adaptive workflow allocation mechanism for anti-money laundering (AML) operations, aiming to improve the accuracy and efficiency of suspicious-transaction review. A multi-agent simulation platform was constructed to model transaction flows, alert generation, and analyst decision behaviors. The system integrates model-confidence estimation, analyst-fatigue prediction, and real-time workload signals to dynamically route alerts. Experiments were conducted using 27.3 million historical transactions and 186,000 alerts from a large commercial financial dataset. Compared with fixed allocation rules, the adaptive mechanism increased alert-escalation precision from 0.32 to 0.46 and recall from 0.70 to 0.78, while reducing average handling time by 19.4%. The proportion of high-risk alerts processed within the target time window improved by 23.8%. These results demonstrate that workflow optimization can meaningfully enhance AML performance beyond model-level improvements.