US Patent Issued to INTERNATIONAL BUSINESS MACHINES on April 7 for "Realistic counterfactual explanation of machine learning predictions" (Israeli, Indian Inventors)

ALEXANDRIA, Va., April 7 -- United States Patent no. 12,596,941, issued on April 7, was assigned to INTERNATIONAL BUSINESS MACHINES Corp. (Armonk, N.Y.).

"Realistic counterfactual explanation of machine learning predictions" was invented by Michael Vinov (Haifa, Israel), Oleg Blinder (Haifa, Israel), Diptikalyan Saha (Bangalore, India), Sandeep Hans (New Delhi), Aniya Aggarwal (New Delhi, Israel), Omer Yehuda Boehm (Haifa, Israel) and Eyal Bin (Haifa, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method comprising, automatically: analyzing a machine learning dataset which comprises multiple datapoints, to deduce constraints on features of the datapoints; generating a first set ...