Bank of America Corporation

Naman Mehra

Aeric John Solow

A method includes accessing the first user data set and the second user data set. The second user data set includes a homomorphically-encrypted data set. The method includes executing a predictive model trained to generate a homomorphically-encrypted recommendation of an identified interaction for a user based at least in part upon the first user data set and the homomorphically-encrypted data set. The user is associated with at least one of the first entity or the second entity. The method further includes transmitting the homomorphically-encrypted recommendation of the identified interaction for the user to a computing system associated with the second database and the second entity, receiving, from the computing system associated with the second database and the second entity, a decrypted recommendation of the identified interaction for the user, and transmitting the decrypted recommendation to a computing system associated with the user.

Growing community of inventors

Charlotte, NC, United States of America

Naman Mehra