Systems and methods for enriching modeling tools and infrastructure with semantics

US12265918B2 · kind B2 · utility

Assignee

• ZestFinance, Inc. · US

Inventors

• Douglas C. Merrill · Los Angeles, US
• Armen Avedis Donigian · Los Angeles, US
• Eran Dvir · Givatayim, IL
• Sean Javad Kamkar · Los Angeles, US
• Evan Kriminger · San Francisco, US
• Vishwaesh Rajiv · Los Angeles, US
• Michael Edward Ruberry · Los Angeles, US
• Ozan Sayin · Los Angeles, US
• Yachen Yan · Los Angeles, US
• Derek Wilcox · Los Angeles, US
• John Candido · Burbank, US
• Benjamin Anthony Solecki · Los Angeles, US
• Jiahuan He · Beijing, CN
• Jerome Louis Budzik · Winthrop Harbor, US
• John J. Beahan · Pasadena, US
• John Wickens Lamb Merrill · Los Angeles, US
• Esfandiar Alizadeh · Santa Monica, US
• Liubo Li · Los Angeles, US
• Carlos Alberta Huertas Villegas · Redondo Beach, US
• Feng Li · Beijing, CN
• Randolph Paul Sinnott, Jr. · Los Angeles, US

Key dates

• Filing date: Nov 7, 2023
• Grant date: Apr 1, 2025
• Expiry date: Nov 7, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F16/9027
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Systems and methods for generating and processing modeling workflows are disclosed. In some examples, a reference distribution of scores generated by a model is determined. The reference distribution of scores is recorded in a structured database. One or more unexpected scores are detected during execution of the model. To detect the one or more unexpected scores, a production distribution of scores is compared with the reference distribution of scores recorded in the structured database. The production distribution of scores is generated by the model for a production input data set. An alert is then provided to an external system, when an alert condition is determined to be satisfied based on the comparison. The alert indicates detection of the one or more unexpected scores.