USPTO Patent Application: Feature Importance System

ChangeBridge: Patent Apps - Business Methods (G06Q)

Detected March 26th, 2026

Summary

The USPTO has published a patent application (US20260087449A1) detailing a feature importance system using probabilistic graphical models and Lasso techniques. The system aims to identify features relevant to predicting target variables, particularly within supply chain contexts.

View original document View source feed page

What changed

This document is a published patent application from the USPTO for a "Class Level Feature Importance Using Lasso and Probabilistic Graphical Models." The application describes a method and system for identifying features crucial to determining whether a target variable will achieve a specific value. Key steps include generating a probabilistic graphical model for supply chain entities, selecting target variables, collating and pruning features, binning features, and modeling a network graph to derive inferences about supply chain target variables.

As this is a patent application, it does not impose direct regulatory obligations or compliance deadlines on entities. However, it represents a novel technological approach that could be adopted by companies involved in supply chain management, data analytics, and AI development. Companies utilizing or developing similar systems may wish to review the patent claims for potential intellectual property considerations.

Source document (simplified)

← USPTO Patent Applications

Class Level Feature Importance Using Lasso and Probabilistic Graphical Models

Application US20260087449A1 Kind: A1 Mar 26, 2026

Inventors

Deb Mohanty, Phani Mitra Bulusu, Rashid Puthiyapurayil, Vidhi Chugh

Abstract

Embodiments of the following disclosure provide a feature importance system and method to identify features relevant to determining whether a target variable will achieve a particular value. One example method includes generating a probabilistic graphical model to represent the performance of one or more entities in a supply chain and selecting or more target variables. The method further includes collating a list of features pertaining to the one or more selected target variables, pruning at least one of the one or more features from the list and generating one or more bins in which to distribute the one or more features in the list. The method further includes modeling a network graph incorporating the one or more features in the list and bins and determining one or more inferences pertaining to the one or more supply chain entity target variables.