Invention Grant
- Patent Title: Memory-free anomaly detection for risk management systems
-
Application No.: US16951995Application Date: 2020-11-18
-
Publication No.: US11374919B2Publication Date: 2022-06-28
- Inventor: Christopher Gabriel Leung
- Applicant: Okta, Inc.
- Applicant Address: US CA San Francisco
- Assignee: Okta, Inc.
- Current Assignee: Okta, Inc.
- Current Assignee Address: US CA San Francisco
- Agency: Fenwick & West LLP
- Main IPC: H04L9/40
- IPC: H04L9/40 ; G06Q20/40

Abstract:
A risk management system deploys an anomaly detection method for a target data instance without explicitly storing data processing architectures in memory. The anomaly detection method determines whether the target data instance is an anomaly with respect to a reference set of data instances. In one embodiment, the anomaly detection method mimics traversal through one or more trees in an isolation forest without explicitly constructing or storing the trees of the isolation forest in memory. This allows the risk management system to avoid unnecessary storage and retrieval of parts of each tree that would not be traversed if the tree were constructed. Moreover, the anomaly detection method allows anomaly detection to be efficiently performed within memory-constrained systems.
Public/Granted literature
- US20220158989A1 MEMORY-FREE ANOMALY DETECTION FOR RISK MANAGEMENT SYSTEMS Public/Granted day:2022-05-19
Information query