Systems and methods for merchant level fraud detection based in part on event timing
Summary
USPTO granted Patent US12597035B2 to Stripe, LLC for a fraud detection system that analyzes merchant transaction timing using machine learning models. The patent covers encoding merchant system data and time-based sequential operation data into inputs for multiple ML models to generate fraud scores. When fraud thresholds are met, remediative actions are triggered against merchant transactions or systems.
What changed
Stripe, LLC received USPTO Patent US12597035B2 covering systems and methods for detecting fraudulent merchant activities on commerce platforms. The patent describes a method involving encoding merchant system data and time-based sequential operation data into input signals, then processing these through separate machine learning models to generate individual fraud scores. These scores are combined into a single merchant fraud score, and when a configurable fraud detection threshold is satisfied, remediative actions are initiated against the merchant transaction or system.
The grant of this patent establishes Stripe's intellectual property rights in fraud detection technology utilizing event timing analysis. Fintech companies, payment processors, and commerce platforms developing competing fraud detection systems should consider potential IP implications and may need to evaluate whether their technologies require licensing or design-around modifications to avoid infringement claims.
What to do next
- Monitor for updates
Archived snapshot
Apr 7, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Systems and methods for merchant level fraud detection based in part on event timing
Grant US12597035B2 Kind: B2 Apr 07, 2026
Assignee
STRIPE, LLC
Inventors
Massoud Hosseinali, Florian Hartl, Efstathios Vafeias, Keagan Long, Stef Nelson-Lindall, Dan Brown
Abstract
A method and apparatus for detecting fraudulent merchant activities at a commerce platform system are described. The method may include accessing a first set of merchant system data and encoding the first set of merchant data into a set of structure data input signals. The method may also include accessing a set of time based data associated a set of sequential operation performed at the commerce platform system in response to the merchant system transaction being processed, and encoding the set of time based data into a set of unstructured time-based data input signals. The method may also include inputting the sets of inputs into different machine learning models to generate different machine learning model scores predictive of merchant fraud. The method may further include generating a single merchant fraud score, and in response to detecting that the single merchant fraud score satisfies a fraud detection threshold, initiating one or more remediative actions against the merchant system transaction, the merchant system, or a combination thereof.
CPC Classifications
G06Q 20/4016 G06N 20/20 G06N 3/045
Filing Date
2022-12-21
Application No.
18086393
Claims
19
Related changes
Get daily alerts for USPTO Patent Grants - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.