Loading patent…
AssigneeVail Systems, Inc.
InventorsSrinivasa C RAO, Todd WHITELEY, Bopsi CHANDRAMOULI, David James FRUIN
Estimating the term…
Methods, systems, and non-transitory computer-readable medium are provided for caller risk scoring using STIR/SHAKEN data. A network fraud detection engine receives attestation and verification status data from a real-time telephony network signaling system and retrieves historical STIR/SHAKEN data from a call authentication database. Attestation-verification pairings are categorized into predefined resolved values, and a caller risk score is computed based on frequency, recency, and contiguity analysis. A weighted risk model applies an appropriate decay function and amplifies contiguous spans of directionally similar values. The computed caller risk score is then transmitted to a service platform for call handling, fraud detection, and routing decisions. The system dynamically adjusts thresholds using machine learning-driven fraud pattern recognition, ensuring adaptive real-time filtering of high-risk inbound calls. This solution enhances telephony security while reducing false positives for legitimate calls.
A method for determining caller risk scoring using STIR/SHAKEN data, the method comprising:
A system for caller risk scoring using STIR/SHAKEN data, the system comprising:
A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause a computing device to perform operations comprising:
Dependencies are inferred from the claim text.