Bank of America Corporation
DYNAMIC INTERACTION OPTIMIZATION AND CROSS CHANNEL PROFILING THROUGH ONLINE MACHINE LEARNING

Abstract:

A system and method for dynamically optimizing channel interactions and account security are provided. A controller configured for analyzing user interactions is configured to determine an interaction pattern of a user during an interaction with the user over a communication channel; calculate a weighted confidence function for subsequent interactions with the user based on the determined interaction pattern, wherein the weighted confidence function defines authentication and response procedures for the subsequent interactions with the user; and merge the weighted confidence function into a custom user profile for the user across a plurality of communication channels, wherein the user profile maps account vulnerabilities based on the weighted confidence function.