Data-driven machine-learning theft detection

US11551227B2 · kind B2 · utility

Assignee

• NCR Corporation · US

Inventors

• Itamar David Laserson · Givat Shmuel, IL
• Avishay Farbstein · Ora, IL
• Tali Shpigel · Bnei Brak, IL
• Mor Zimerman Nusem · Be'er Gannim, IL

Key dates

• Filing date: Aug 29, 2019
• Grant date: Jan 10, 2023
• Expiry date: Mar 6, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G07G3/003
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

A machine-learning algorithm is trained with features relevant to basket data for items of transactions. The trained algorithm is trained to predict whether a given transaction is more or less likely to be associated with theft being engaged in by a transaction operator for the transaction. The trained algorithm is then provided basket data for a given transaction and produces as output a theft prediction value. When the theft prediction value exceeds a configured threshold value, the transaction is flagged for manual intervention or the transaction is flagged for subsequent manual verification.