Bank of America Corporation
SYSTEMS AND METHODS FOR INCREMENTAL LEARNING AND AUTONOMOUS MODEL RECONFIGURATION IN REGULATED AI SYSTEMS

Abstract:

Embodiments of the system, as described herein leverage artificial intelligence, machine-learning, and/or other complex, specific-use computer systems to provide a novel approach for identifying patterns in input data and determine and implement necessary changes to a regulated ML model within the bounds of a regulatory control structure. The system utilizes a collection of machine learning models, either individually or clustered, to process incoming data to determine if specific data should be flagged as irregular or part of the formation of an emerging pattern. The system may intelligently analyze such patterns to determine any regulatory implications that may arise from acting on or adapting to the perceived patterns.