Amazon Fraud Detector website screenshot

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 7 Features
Financial 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...

Collections

Arazzo Workflows

Amazon Fraud Detector Author Rule

Create a DETECTORPL rule for a detector and read the detector's rules back to confirm it.

ARAZZO

Amazon Fraud Detector Bootstrap Event Type

Create fraud and legit labels, define an event type that uses them, then confirm the event type exists.

ARAZZO

Amazon Fraud Detector Decommission Detector

Inspect a detector's rules and then delete the detector, branching when rules still block deletion.

ARAZZO

Amazon Fraud Detector Detector Pipeline

Define an event type, create a detector and a rule, then score a sample event against the detector.

ARAZZO

Amazon Fraud Detector Inventory Models and Detectors

List models for an event type, then list detectors and tag a chosen detector with its model count.

ARAZZO

Amazon Fraud Detector Provision Model and Detector

Define an event type, create an ML model and a detector on top of it, then confirm the detector exists.

ARAZZO

Amazon Fraud Detector Score Event and Tag

Score an event against a detector and branch on the returned model score to tag the detector accordingly.

ARAZZO

Amazon Fraud Detector Tag and Audit Resource

Assign tags to a Fraud Detector resource and read its tags back to confirm they were applied.

ARAZZO

Pricing Plans

Rate Limits

Amazon Fraud Detector Rate Limits

5 limits

RATE LIMITS

FinOps

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.

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

JSON Structure

Amazon Fraud Detector Detector Structure

0 properties

JSON STRUCTURE

Amazon Fraud Detector Event Type Structure

0 properties

JSON STRUCTURE

Amazon Fraud Detector Model Structure

0 properties

JSON STRUCTURE

Amazon Fraud Detector Rule Structure

0 properties

JSON STRUCTURE

Amazon Fraud Detector Tag Structure

0 properties

JSON STRUCTURE

Example Payloads

Resources

🔗
PostmanWorkspace
PostmanWorkspace
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🌐
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
🔗
Vocabulary
Vocabulary
🔗
JSONLD
JSONLD

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: Amazon Fraud Detector API
  version: '2019-11-15'
request:
  auth:
    type: apikey
    key: Authorization
    value: '{{Authorization}}'
    placement: header
items:
- info:
    name: Detectors
    type: folder
  items:
  - info:
      name: Get Detectors
      type: http
    http:
      method: POST
      url: https://frauddetector.{region}.amazonaws.com/detectors
      body:
        type: json
        data: '{}'
    docs: Gets all detectors or a single detector if a detectorId is specified.
  - info:
      name: Put Detector
      type: http
    http:
      method: PUT
      url: https://frauddetector.{region}.amazonaws.com/detectors
      body:
        type: json
        data: '{}'
    docs: Creates or updates a detector.
  - info:
      name: Delete Detector
      type: http
    http:
      method: DELETE
      url: https://frauddetector.{region}.amazonaws.com/detectors/:detectorId
      params:
      - name: detectorId
        value: ''
        type: path
        description: The ID of the detector to delete.
    docs: Deletes the detector. Before deleting a detector, you must first delete all detector versions and rule versions
      associated with the detector.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: Get Models
      type: http
    http:
      method: POST
      url: https://frauddetector.{region}.amazonaws.com/models
      body:
        type: json
        data: '{}'
    docs: Gets one or more models.
  - info:
      name: Put Model
      type: http
    http:
      method: PUT
      url: https://frauddetector.{region}.amazonaws.com/models
      body:
        type: json
        data: '{}'
    docs: Creates or updates a model.
- info:
    name: Rules
    type: folder
  items:
  - info:
      name: Get Rules
      type: http
    http:
      method: POST
      url: https://frauddetector.{region}.amazonaws.com/rules
      body:
        type: json
        data: '{}'
    docs: Gets all rules for a detector.
  - info:
      name: Create Rule
      type: http
    http:
      method: PUT
      url: https://frauddetector.{region}.amazonaws.com/rules
      body:
        type: json
        data: '{}'
    docs: Creates a rule for use with the specified detector.
- info:
    name: Predictions
    type: folder
  items:
  - info:
      name: Get Event Prediction
      type: http
    http:
      method: POST
      url: https://frauddetector.{region}.amazonaws.com/predictions/event/:eventId
      params:
      - name: eventId
        value: ''
        type: path
        description: The unique ID of the event.
      body:
        type: json
        data: '{}'
    docs: Evaluates an event against a detector version and returns prediction outcomes.
- info:
    name: Event Types
    type: folder
  items:
  - info:
      name: Get Event Types
      type: http
    http:
      method: POST
      url: https://frauddetector.{region}.amazonaws.com/event-types
      body:
        type: json
        data: '{}'
    docs: Gets all event types or a specific event type if a name is provided.
  - info:
      name: Put Event Type
      type: http
    http:
      method: PUT
      url: https://frauddetector.{region}.amazonaws.com/event-types
      body:
        type: json
        data: '{}'
    docs: Creates or updates an event type.
- info:
    name: Labels
    type: folder
  items:
  - info:
      name: Put Label
      type: http
    http:
      method: PUT
      url: https://frauddetector.{region}.amazonaws.com/labels
      body:
        type: json
        data: '{}'
    docs: Creates or updates label. A label classifies an event as fraudulent or legitimate.
- info:
    name: Tags
    type: folder
  items:
  - info:
      name: List Tags For Resource
      type: http
    http:
      method: GET
      url: https://frauddetector.{region}.amazonaws.com/tags/:resourceARN
      params:
      - name: resourceARN
        value: ''
        type: path
        description: The ARN of the resource.
    docs: Lists all tags associated with the resource.
  - info:
      name: Tag Resource
      type: http
    http:
      method: POST
      url: https://frauddetector.{region}.amazonaws.com/tags/:resourceARN
      params:
      - name: resourceARN
        value: ''
        type: path
        description: The ARN of the resource.
      body:
        type: json
        data: '{}'
    docs: Assigns tags to a resource.
bundled: true