SYSTEM FOR ANOMALY DETECTION AND REMEDIATION BASED ON DYNAMIC DIRECTED GRAPH NETWORK FLOW ANALYSIS

摘要

Embodiments of the present invention provide a system for anomaly detection and remediation based on dynamic directed and undirected graph network flow analysis. Information for multiple accounts is extracted to generate a plurality of dynamic directed and undirected graphs made up of multiple nodes and edges. The nodes represent at least one of the multiple accounts, and each edge represents at least an association or transfer between two nodes. A custom entropy and divergence value is determined for each pair of nodes linked by an edge, as compared to similar or related nodes and edges. A nodal set of a first node and multiple additional nodes linked to the first node by an edge is identified as having a custom entropy and divergence value associated with anomalous directional flow. In response, a remediation action is executed with respect to one or more accounts associated with the nodal set.