OnerShield

Manage risk to prevent fraud

Identify and block fraud in real-time with AI models fueled by global intelligence, maximizing legitimate revenue.

Fraud Rate

0.07 %

Early Fraud Warning

0.03%

Jan 1Jan 10

User profile data

Identity signals, device fingerprints, behavioral baselines, and identity graphs for individual anomaly detection.

Transaction data

Card details, amounts, frequency, addresses, and history to model payment behavior and detect coordinated attacks.

Card network alerts

Visa/Mastercard TC40s, SAFE reports, and early dispute notifications to identify fraud before chargebacks.

Third-party intelligence

Global threat feeds (Cybersource, Maxmind, LexisNexis) and AML sanctions lists for cross-platform prevention.

Feature profiling engine

Combines real-time behavioral metrics with relational mapping to track complex user networks and automate feature extraction for precise model training.

Automated machine learning center

Powers millisecond-level detection through automated training and real-time inference across supervised, unsupervised, and scenario-based models.

High-Value Transaction Rule

Transaction Amountis greater than5,000

AND

Card Txn Count 24hexceeds10

Fraud Risk Scoreis greater than85

OR IF

Rule configuration

Set flexible, lifecycle-wide risk actions like 3DS and automated blocking—while leveraging whitelists, blacklists, and BIN rules for precise enforcement.

Scenario NameIssuing Risk Control

Strategies (5)

NameDescriptionPriorityRules

Active

Scenario templates

Configure once, deploy anywhere for multi-scenario efficiency

Strategy discovery lab

Run A/B tests and backtests, leveraging ML for strategy suggestions and adaptive risk scoring.

Real-time monitoring

Monitor transactions for real-time anomalies and manage post-event cases through geo-validation and delayed clearing.

Strategy

Customized service

Deliver tailored strategy configuration and continuous tuning per merchant.

Strategy performance analysis

Evaluate strategies using real-time and historical data to identify redundant rules and support continuous, dynamic tuning.

Offline data analysis

Analyze historical data to uncover fraud rings and attack patterns, using user segmentation to drive long-term risk planning.

Risk profiling & attribution

Create unified risk profiles from cross-channel data and leverage attribution modeling to trace sources and identify fraud patterns.

The Rise of Cross-Border Card Payments: Transforming Global Transactions

18 Apr 2025

Understanding and Reducing the Cost of Cross-Border Payments