SEON helps online businesses stop fraud and meet anti-money laundering (AML) obligations from one platform. Fintechs, payment firms, iGaming operators and retailers use it to score risk in real time, verify customers at onboarding, screen people and payments against sanctions lists and investigate suspicious activity.
Fraud and AML data sit together, so the same signals that flag a risky signup also inform compliance checks later in the customer relationship. Fraud and compliance teams therefore work from one record of each customer instead of reconciling two systems.
At A Glance
| Vendor | SEON |
|---|---|
| Category | Fraud prevention, AML compliance and identity verification |
| Identities covered | Customers and end users of online businesses, their devices, emails, phone numbers and payments |
| Deployment | Cloud platform accessed through APIs, SDKs and the SEON Admin panel |
| Agentic AI | AI agent and bot detection, an AML screening agent, AI assistance for rules and investigations |
| Customers | Plaid, Revolut, Mollie, Nexi, Entain |
| Founded | 2017 |
| Market classification | Fraud Prevention; also Identity Verification |
What SEON Does
Online businesses want to approve good customers quickly while keeping out fraudsters, bonus abusers and money launderers. SEON’s answer is to enrich every interaction with risk signals drawn from its own first-party data, such as a person’s digital footprint and the device they are using, then score that risk with machine learning and act on it automatically. The aim is “to enable companies to prevent fraud without impeding legitimate growth.” Customers go live quickly, with a reported average of 14 days from implementation to impact.
Products
Fraud Prevention
The fraud modules decide in real time whether a signup, login, transaction or promotion claim is risky. Digital footprint analysis uses social and digital signals to judge whether an identity is genuine. Device intelligence combines behavioural and hardware signals to catch bots, account takeovers and multi-accounting, and behavioural biometrics plus AI agent and bot detection separate people from automated traffic. Everything feeds an AI risk score that drives automated decisions.
Identity & KYC
For onboarding, SEON pairs ID and document verification with behaviour-based signals, so KYC goes beyond checking the document alone.
- Passive liveness detection for deepfakes, replays and spoofing
- Proof of address checks that catch tampered or AI-generated documents
- Workflow orchestration to build verification journeys
AML & Compliance
Compliance teams use these modules to meet screening and monitoring obligations without a separate AML system.
- Customer screening with fuzzy matching and jurisdiction-based risk profiles
- Payment screening of senders, receivers, wallets and bank IDs against sanctions lists
- Transaction monitoring with no-code rules and velocity controls
- AI support for drafting suspicious activity reports and for pre-KYC screening
Platform
Shared tooling ties the modules together: rules and AI risk decisioning, case management for fraud and AML investigations, an AI investigation tool and managed risk services for teams that want SEON analysts involved.
How It Works
SEON runs as a cloud service. Data flows in three ways:
| Device signals | A CDN-hosted JavaScript snippet for web apps and iOS and Android SDKs collect device data, which is encrypted on the device before it is sent |
|---|---|
| Decision calls | The Fraud API takes email, phone, IP, BIN and AML checks plus device data in one call and returns enriched data, rule results and a score; the Workflow API runs verification sessions through hosted flows, with event-driven webhooks back to the customer |
| Feedback | The Label API returns confirmed outcomes to SEON’s models, and an Erase API deletes a user’s data on request |
Analysts review results in the SEON Admin panel, or enrich data by hand on the Manual Lookup page without any integration.
Identities And Systems Covered
| Customers and end users | Verification, liveness and proof of address at onboarding, then login and activity monitoring |
|---|---|
| Devices | Fingerprinting across web, iOS and Android, including jailbreak status on iOS |
| Digital identifiers | Email addresses, phone numbers and IP addresses |
| Payments | Card BIN data, senders, receivers, wallets and bank IDs |
| Organisations | Sanctions and watchlist searches through the AML Entity API |
| Automated traffic | Bots and AI agents acting on customer-facing services |
Agentic AI Capabilities
AML Screening Agent
An AI agent reviews each screening hit against the customer’s own data, flags likely false positives and gives its rationale for every finding, which reduces the manual triage behind sanctions and PEP alerts.
AI Assistance For Analysts
- AI summaries that explain why a transaction was approved, flagged or blocked
- AI rules, where users describe what they want to detect and AI drafts an editable rule
- Score explainability that ranks the signals behind each score
- Network analysis that maps relationships across shared devices, IPs and emails by connection strength
- Daily model retraining on transactions with confirmed outcomes
Company Background
| Founded | January 2017, by Tamás Kádár and Bence Jendruszák |
|---|---|
| Offices | Austin, London, Budapest and Jakarta |
| Leadership | Tamás Kádár (CEO), Bence Jendruszák (COO), Shaun Worley (Chief Product Officer), Alan Lipton (CTO), Ken Talanian (CFO) |
| Funding | A Series A in March 2021 led by Creandum and an $80 million Series C, which is going into expansion in Asia-Pacific and Latin America |
| Scale | More than 5,000 reported business customers and a team of over 400 |
Note: This overview is compiled from SEON’s publicly available information as of 3 November 2026. It is provided for information only. NHI Mgmt Group does not endorse any vendor, and nothing on this page represents the opinions of NHI Mgmt Group.