Identify fraudulent online activities
Globally each year, tens of billions of dollars are lost to online fraud. Traditionally, companies used rule-based fraud detection applications that aren't accurate enough and can’t keep up with the changing behaviors of fraudsters. With AWS Fraud Detection machine learning solutions, companies can proactively and more accurately detect and prevent online fraud. These solutions will help reduce revenue losses, avoid brand damage, and provide a frictionless customer online experience while adapting to changing threat patterns.
Fraud detection on your own terms
Companies that do not have machine learning experts, can use Amazon Fraud Detector to add ML-based fraud detection capabilities to their business applications in minutes while companies with a dedicated team of data scientists can use Amazon SageMaker to develop highly specialized fraud detection solutions in days.
Built on Amazon's fraud detection expertise
Amazon's Fraud Detection ML solutions leverages Amazon's 20 years of experience preventing fraud and abuse at AWS, Amazon.com, and subsidiary businesses to enrich the models it produces with knowledge of fraud patterns.
Prevent and detect online fraud in real-time
Amazon's Fraud Detection ML solutions scores the risk of an event in real-time, allowing customers to instantly apply containment or remediation measures designed to block or deny fraudsters and fast-track low-risk activity to provide better customer experiences for legitimate customers.
Give fraud teams more control
By automatically handling the complex tasks required to train, tune, and deploy a fraud detection model, Amazon's Fraud Detection ML Solutions make it possible for users who aren’t machine learning experts, but are familiar with fraud issues, to participate in developing and updating highly accurate models.
Payment or transaction fraud detection
The event of interest is an attempt to complete an online purchase or make or process a payment online. One common example in the e-commerce space relates to a “guest checkout”. The transaction involves a user who does not have account history or has selected a “guest” checkout option for a more anonymous experience.
New account fraud
The event of interest is the act of signing up or registering for a new account. Fraud starts when a bad actor creates a fake, stolen, synthetic identities, or generate multiple accounts, often through the use of bots. Once identity is established on a digital platform, executing an attack is easier.
The event of interest is a login attempt for a legitimate user account. Account Takeover refers to the situation where a legitimate user’s login has been compromised, either because a bad actor has stolen their userid and password, purchased them on the dark web, or managed to guess it.
The event of interest is typically the act of a user redeeming a benefit granted via a demand generation or marketing promotion. Bad actors will access a legitimate user’s account and drain loyalty credits or points via transfer or purchase. They will also create multiple fake accounts to exploit promotions such as a free trial or free credits that come with a new account, or perform a self-referral to get a referral bonus.
Fake or Abusive Reviews
The event of interest is the posting of a product review which may contain misleading or abusive content. Automating screening is critical for scaling the ability to spot fake and abusive reviews so that customer service teams don’t have to wade through mountains of alerts, many of which may be false positives.
During online account registration, machine learning-powered facial biometrics can enable identity verification for any situation. With pre-trained facial recognition and embedded analysis capabilities, you can add this to enhance your user onboarding and authentication workflow with no machine learning expertise required.
Featured Solutions on AWS
Discover Purpose-Built Services, AWS Solutions, Partner Solutions, and Guidance to rapidly address your business and technical use cases.
Fraud Detection Using Machine Learning
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 that can be modified to work with any dataset.
Guidance for Near Real-Time Fraud Detection with Graph Neural Network on AWS
This Guidance demonstrates an end-to-end, near real-time anti-fraud system based on deep learning graph neural networks. This blueprint architecture uses Deep Graph Library (DGL) to construct a heterogeneous graph from tabular data and train a Graph Neural Network (GNN) model to detect fraudulent transactions.
SLA Digital creates new revenue streams for mobile operators and online merchants around the world through seamless and secure carrier billing solutions. SLA Digital provides a carrier billing platform that enables merchants to easily connect with mobile operators; reducing costs, operational risks, and time to market for both parties. As a payment aggregator, identifying and preventing fraudulent transactions is crucial to SLA Digital’s business.
"Twelve months ago, we were looking for a fraud detection solution that didn’t require us to invest heavily in our own machine learning expertise. With transparent pay-as-you-use pricing, Amazon Fraud Detector helped us to easily create and incorporate an effective and affordable new machine learning model into our existing setup."
Richard Fisher, Head of Technology at SLA Digital
FlightHub Group makes travel accessible, allowing more people to visit new places and explore new cultures. With over 5 million customers served per year, their goal is to provide travelers with the cheapest flights available, along with optimal itineraries and exceptional customer service. One of the highest priorities for FlightHub's Fraud Prevention team is discerning a value-conscious traveler seeking an affordable airline ticket from fraudsters seeking to buy tickets with stolen credit cards.
"Since introducing Amazon Fraud Detector, our abort rate has dropped below 2% (vs. 5% previously). Additionally, our chargeback rate is the lowest it’s ever been since the company’s inception. The business can now accept more checkouts that our past models would have flagged as risky and turned away. But perhaps the best thing is we’re getting these great results with roughly the same operational costs as before. All of this results in an increased number of bookings and revenues, along with a decrease in losses due to chargebacks."
Drayton Williams, Fraud Investigations Manager at FlightHub
“Identity verification and validation have been a major challenge in emerging markets. The ability to properly identify users is a key hindrance in building credit for billions of people in emerging markets. Using Amazon Rekognition for identity verification on our mobile application has reduced verification errors significantly and given us the ability to scale. We can now detect and verify an individual’s identity in real time without any human intervention, thereby allowing faster access to our products. We tried various well-advertised solutions, but none of the popular alternatives could accurately map out various skin tones. Amazon Rekognition helped us effectively recognize faces of our customers in our markets. It also helped us with KYC in discovering overlapping profiles and duplicate datasets.”
Wale Akanbi, CTO & Co-Founder - Aella Credit
“In Q1/Q2 2020 we experienced a spike in accounts being used for phishing attacks. As a result, we needed to supplement our existing homegrown solution with stronger transaction data and signals to identify bad actors sooner. A scalable solution based on predictive machine-learning was important to us as a growing business ourselves. Amazon Fraud Detector made it easy to build a model using our own data that accurately identifies account signups that result in phishing attacks. More importantly, we were able to get these results with a very low false positive rate, which means no additional work for our operations staff. Amazon Fraud Detector has a competitive pricing model and we can easily integrate the model into our existing workflow.”
Alex Burch, Senior Email Operations Engineer - ActiveCampaign
“Amazon Fraud Detector has been a great addition to our Fraud detection and mitigation capability. The ability to write custom rules that apply to our unique situation, train ML models on-demand, and seamless integration with other AWS services has enabled us to make decisions quickly and intelligently while retaining complete control of the platform. AWS was very helpful during the proof of concept stage and has been adding new features to the platform inline with Fraud trends.”
Mary Criniti, CTO - Qantas Loyalty
"With Amazon Fraud Detector, we reduced fraudulent transactions by 6%. At the same time, we’ve been able to automate checkout fulfillment on more than 90% of the transactions that would have previously been flagged for manual review. Now, we’re manually reviewing less than 1% of our transactions—down from 10%. Since we implemented this service, we’ve seen a significant improvement in our Trustpilot score, and we know it’s a result of this checkout detection automation, as well as additional enhancements we are consistently making on the website. Trust is a big part of our value to customers, so that’s a huge win for our business.”
Kevin Cole, Operations Director - Omnyex
"Amazon Fraud Detector has enabled us to drastically improve operations, increase our flexibility to respond to bad actors, and have greater control of systems and processes. Initially, we were exploring an in-house and 3rd party solution. When Amazon Fraud Detector was announced, we immediately changed course. We have been an AWS customer for many years and have great trust in Amazon’s products. With Amazon Fraud Detector, we are no longer bound by the conventional limitations of on-premise or SaaS offerings. Instead, we have the flexibility to adapt a Machine Learning powered service to meet our needs and the ability to use AWS’s rules-only option while easily scaling to full Machine Learning capabilities when needed. This saved Truevo 3-6 months in development! In fact, we deployed our first prototype model within 30 minutes. Overall, we are operating with greater confidence in our ability to detect fraud in real-time. We are better equipped to deploy rule detections when we notice odd activity that we may not fully understand, but need to stop. We are able to respond and adapt to ever-changing regulatory and scheme requirements allowing us to stay on top of our game.”
Charles Grech, COO - Truevo
Ready to get started?
Contact us for more information on machine learning solutions for Fraud Detection
Contact the AWS Partner Network, to work with our global technology and consulting partners
Use Amazon Fraud Detector to develop your own fraud detection solution