US Patent Issued to Fair Isaac on Sept. 22 for "Latent feature based model bias mitigation in artificial intelligence systems" (California Inventors)

ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,743,601, issued on Sept. 22, was assigned to Fair Isaac Corp. (Minneapolis).

"Latent feature based model bias mitigation in artificial intelligence systems" was invented by Scott Michael Zoldi (San Diego) and Shafi Ur Rahman (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "To eliminating bias from artificial intelligent (AI) systems, a list of class identifiers and features derived from class identifiers represented in training data fed to an AI system are identified for purpose of training a predictive model. Correlation analysis of input features is conducted from a list of raw variables, r, in a dataset and a plurality of derived features, ...