Dynamic multi-model monitoring and validation for artificial intelligence models

US12299140B2 · kind B2 · utility

Assignee

• CITIBANK, N.A. · US

Inventors

• Sofia Rahman · New York, US
• James Myers · New York, US
• Prashant Praveen · New York, US
• Shardul Malviya · London, GB
• Wayne Liao · London, GB
• Deepak Jain · Garland, US
• Samantha Cory · London, GB
• Mariusz Saternus
• Daniel Lewandowski
• Biraj Krushna Rath · London, GB
• Stuart Murray · London, GB
• Philip Davies · London, GB
• Payal Jain · London, GB
• Tariq Husayn Maonah · London, GB
• Vishal Mysore · Mississauga, CA
• Ramkumar Ayyadurai · Jersey City, US
• Chamindra Desilva · London, GB
• William Franklin Cameron · Jacksonville, US
• Miriam Silver · Tel Aviv-Yafo, IL
• Prithvi Narayana Rao · Allen, US
• Pramod Goyal · Ahmedabad, IN
• Manjit Rajaretnam · Irving, US

Key dates

• Filing date: Nov 14, 2024
• Grant date: May 13, 2025
• Expiry date: Nov 14, 2044

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N5/045
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

The systems and methods disclosed herein receives artifacts generated using a first set of models within a multi-model superstructure. The multi-model superstructure includes a second set of models to test the first set of models. The multi-model superstructure dynamically routes the artifacts of the first set of models to one or more models of the second set of models by (i) determining a set of dimensions of the artifacts against which to evaluate the artifacts and (ii) identifying the models in the second set used to test the particular dimension. The second set of models then assesses each artifact against a set of assessment metrics. If an artifact fails to meet one or more assessment metrics, the second set of models generates actions to align the artifact with the set of assessment metrics.