Fraud Detection Using Machine Learning

Fraud Detection Using Machine Learning deploys a machine learning (ML) model and an example dataset of credit card transactions to train the model to recognize fraud patterns. The model is self-learning which enables it to adapt to new, unknown fraud patterns.

Use this Guidance to automate the detection of potentially fraudulent activity, and the flagging of that activity for review. Fraud Detection Using Machine Learning is easy to deploy and includes an example dataset but you can modify the code to work with any dataset.

Overview

Fraud Detection Using Machine Learning allows you to run automated transaction processing on an example dataset or your own dataset. The included ML model detects potentially fraudulent activity and flags that activity for review. The diagram below presents the architecture you can build using the example code on GitHub.

Fraud Detection Using Machine Learning architecture

The code deploys the following infrastructure:

  1. An Amazon Simple Storage Service (Amazon S3) bucket containing an example dataset of credit card transactions.
  2. An Amazon SageMaker notebook instance with different ML models that will be trained on the dataset.
  3. An AWS Lambda function that processes transactions from the example dataset and invokes the two Amazon SageMaker endpoints that assign anomaly scores and classification scores to incoming data points.
  4. An Amazon API Gateway REST API invokes predictions using signed HTTP requests.
  5. An Amazon Kinesis Data Firehose delivery stream loads the processed transactions into another Amazon S3 bucket for storage.
The Guidance also provides an example of how to invoke the prediction REST API as part of the Amazon Sagemaker notebook.
 
When the transactions have been loaded into Amazon S3, you can use analytics tools and services, including Amazon QuickSight, for visualization, reporting, ad-hoc queries, and more detailed analysis.

Fraud Detection Using Machine Learning

Version 2.0.0
Last updated: 01/2022
Author: AWS

Additional resources

Did this Guidance help you?
Provide feedback 

Features

Customizable

This Guidance includes an example dataset of credit card transactions but you can modify the solution to use your own dataset.

Automation

Detect potentially fraudulent activity and flag that activity for review with a pre-built, self-learning ML model.
Video
Solving with AWS Solutions: Fraud Detection Using Machine Learning
Back to top 
Build icon
Deploy an AWS Solution yourself

Browse our library of AWS Solutions to get answers to common architectural problems.

Learn more 
Find an APN partner
Find an AWS Partner Solution

Find AWS Partners to help you get started.

Learn more 
Explore icon
Explore Guidance

Find prescriptive architectural diagrams, sample code, and technical content for common use cases.

Learn more