US Patent Issued to International Business Machines on Feb. 17 for "Fraud detection using multi-task learning and/or deep learning" (Connecticut, Illinois, New York Inventors)

ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,555,114, issued on Feb. 17, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Fraud detection using multi-task learning and/or deep learning" was invented by Jeetu Raj (Urbanna, Ill.), Erik Richter Altman (Danbury, Conn.), Shyam Ramji (Lagrange, N.Y.) and Ravi Nair (Briarcliff Manor, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Application of multi-task learning technique(s) to machine logic (for example, software) used to detect financial transactions that are fraudulent or at least considered likely to be fraudulent. Some embodiments include adjustments and/or additions to conventional multi-task learning techniques in orde...