Learned Execution Graphs for Anomaly Detection & Drift in APIs — Ritvik Pandya, JP Morgan Chase
JP Morgan's payments team uses learned execution DAGs to automate API anomaly and drift detection
Ritvik Pandya from JP Morgan Chase describes a system of short-lived 'execution graphs' modeled as DAGs to represent end-to-end API request flows in their payments infrastructure. The approach enables tiered anomaly detection — skipping deep checks when baselines match — to reduce manual monitoring work and resource overhead. It is a practical MLOps/observability pattern from a major financial institution, relevant to AI-adjacent engineering but not a landmark AI industry signal.