Machine learning model identifies anomalous item pairs

ChangeBridge: Patent Apps - Business Methods (G06Q)

Published April 2nd, 2026

Detected April 2nd, 2026

Summary

The USPTO published patent application US20260094191A1 by inventors Tamar Miriam Haizler and Shiran Abadi, disclosing a machine learning system for identifying anomalous item pairs. The system constructs datasets of item pairs from sales lists, extracts pairwise measures, and applies anomaly detection to flag unusual associations. This technology has applications in e-commerce fraud detection and recommendation systems.

View original document View source feed page

What changed

The patent application discloses a system and method for determining anomalous item pairs using machine learning. The technique involves obtaining a list of items for sale, constructing a dataset of all possible item pairs, extracting multiple sets of pairwise measures for each pair, and applying an anomaly detection model to identify suspicious associations. The system then outputs anomalous item pairs as associated items for further review.

Patent publications do not impose compliance obligations on third parties. Technology companies developing e-commerce platforms, fraud detection systems, or recommendation engines may wish to review this filing for prior art purposes or to identify potential licensing opportunities. No regulatory deadlines or enforcement implications arise from this publication.

Source document (simplified)

← USPTO Patent Applications

MACHINE LEARNING MODEL FOR ASSOCIATING ITEMS

Application US20260094191A1 Kind: A1 Apr 02, 2026

Inventors

Tamar Miriam Haizler, Shiran Abadi

Abstract

System and techniques may be used for determining anomalous item pairs using machine learning. An example technique may include obtaining a list of items for sale, constructing a dataset of pairs of items including each possible item pair of items in the list of items for sale, and extracting a plurality of sets of pairwise measures for each pair of the pairs of items in the dataset, the plurality of sets of pairwise measures including a plurality of pairwise measures for each pair of the pairs of items in the dataset. The example technique may include determining a set of anomalous item pairs of the pairs of items using an anomaly detection model based on the plurality of sets of pairwise measures, and outputting the set of anomalous item pairs as associated items.