DETECTING SUPPLIER FRAUD FROM DIGITAL TRANSACTIONAL DATA

Patent №

US 11,645,661

Granted

2023-05-09

Filed 2020

Owner

COUPA SOFTWARE INCORPORATED

Lab

AI components

3

nlp · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

17135485

A fraud detection system for detecting fraudulent acts related to payment discounts from digital transactional data is disclosed. In some embodiments, the fraud detection system is programmed or configured with data structures and/or database records that are arranged to detect an occurrence of a triggering event, such as receiving an early payment discount by a buyer account from a supplier account. The fraud detection system is programmed to analyze how a first amount charged for certain items by the supplier account to the buyer account before the triggering event has changed to a second amount after the triggering event from digital documents related to procurement transactions. The certain items may include items for sale or for other miscellaneous items. The digital documents may include catalogs, purchase requisitions, purchase orders, or invoices. The fraud detection system is programmed to further detect any potential fraud committed by the supplier account based on the analysis result. Finally, the fraud detection system is programmed to send a warning of the potential fraud to other buyer accounts that have been offered promotions, such as the early payment discounts, from the supplier account.

Natural languagePlanningAI hardwareG06Q 30/0185G06Q 30/0609G06Q 30/0635G06Q 40/12

AI classification

Planning1.00
Natural language0.95
AI hardware0.50
Evolutionary computation0.21
Knowledge representation0.16
Vision0.00
Machine learning0.00
Speech0.00

Ownership

COUPA SOFTWARE INCORPORATED

assignment · 575310097

Assignors

HARRIS, SCOTT, KOROBOV, DMITRI

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC