Finance
KakaoBank upgrades financial fraud detection with context-aware AI
KakaoBank has applied an AI-based financial fraud detection model to its abnormal transaction detection system, analyzing customer behavior before and after transactions. The \"sequence detection model\" uses an attention mechanism to assess transaction order, time gaps between actions and device-change patterns, and can spot pauses and resumptions in activity. KakaoBank said prevention cases rose 4.4 times on a monthly average after a pilot. In the first quarter, it detected 49.8 percent of suspected cases independently.
