US Patent Issued to Capital One Services on March 17 for "Counterfactual samples for maintaining consistency between machine learning models" (New York, Massachusetts, District Of Columbia Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,579,479, issued on March 17, was assigned to Capital One Services LLC (McLean, Va.).

"Counterfactual samples for maintaining consistency between machine learning models" was invented by Samuel Sharpe (Cambridge, Mass.), Christopher Bayan Bruss (Washington) and Brian Barr (Schenectady, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "In some aspects, a computing system may aggregating multiple counterfactual samples so that machine learning explanations can be generated for sub-populations. In addition, methods and systems described herein use machine learning and counterfactual samples to determine text to use in an explanation for a model's predict...