Amazon Fraud Detector logo

Amazon Fraud Detector

Amazon Fraud Detector is a fully managed service that uses machine learning to identify potentially fraudulent activities and accurately distinguish between legitimate and high-risk transactions. It uses your data and the same technology that Amazon uses to protect its own business from fraud.

1 APIs 1 Capabilities 7 Features
AWSFinancial ServicesFraud DetectionMachine LearningSecurity

APIs

Amazon Fraud Detector API

The Amazon Fraud Detector API provides programmatic access to create and manage detectors, models, event types, entities, labels, outcomes, rules, and variables for automated fr...

Capabilities

Amazon Fraud Detector Real-Time Detection

Orchestrate ML models and business rules for real-time transaction fraud scoring and decision-making.

Run with Naftiko

Features

No ML Expertise Required

Automatically trains and deploys ML models using your historical transaction data without requiring ML expertise.

Real-Time Fraud Scoring

Returns fraud scores within milliseconds for integration into transaction approval flows.

Pre-Built Models

Online Fraud Insights (OFI), Transaction Fraud Insights (TFI), and Account Takeover Insights (ATI) pre-trained model types.

Rule Engine

DETECTORPL rule language allows writing conditional logic using model scores and event variables.

Model Explainability

Variable importance scores explain which factors most influenced a fraud prediction.

Cold Start Protection

Uses Amazon fraud experience to provide immediate predictions even with limited historical data.

Event Ingestion

Ingest historical labeled events to continuously improve model accuracy over time.

Use Cases

Payment Fraud Detection

Score credit card and payment transactions in real-time to block fraudulent purchases.

Account Takeover Prevention

Detect unauthorized login attempts and account compromise using behavioral signals.

New Account Fraud

Identify fraudulent new account registrations at signup to prevent synthetic identity fraud.

Promotion Abuse Detection

Flag users abusing discount codes, referral bonuses, and promotional offers.

Chargeback Prevention

Reduce chargeback rates by blocking high-risk transactions before they complete.

Insurance Claims Fraud

Score insurance claims for fraudulent patterns in real-time during claim submission.

Integrations

Amazon S3

Store training datasets and export labeled event data to S3 for model training.

AWS IAM

Control access to detectors, models, and predictions using IAM roles and policies.

Amazon SageMaker

Combine Fraud Detector with SageMaker for custom ML pipelines and model integration.

Amazon CloudWatch

Monitor prediction volumes, model performance, and API error rates.

AWS KMS

Encrypt training data and model artifacts with customer-managed KMS keys.

Amazon EventBridge

Route fraud detection outcomes to downstream systems for automated response workflows.

Amazon SNS

Send real-time fraud alert notifications to operations teams via SNS topics.

Semantic Vocabularies

Amazon Fraud Detector Context

5 classes · 12 properties

JSON-LD

API Governance Rules

Amazon Fraud Detector API Rules

25 rules · 7 errors 16 warnings 2 info

SPECTRAL

Resources

🌐
Portal
Portal
🔗
Website
Website
🔗
Documentation
Documentation
📜
TermsOfService
TermsOfService
📜
PrivacyPolicy
PrivacyPolicy
💬
Support
Support
📰
Blog
Blog
👥
GitHubOrganization
GitHubOrganization
🌐
Console
Console
📝
SignUp
SignUp
🟢
StatusPage
StatusPage
👥
YouTube
YouTube
👥
StackOverflow
StackOverflow
🔗
SpectralRules
SpectralRules
🔗
NaftikoCapability
NaftikoCapability
🔗
NaftikoCapability
NaftikoCapability
🔗
Vocabulary
Vocabulary
🔗
JSON-LD
JSON-LD