Industry-wide ecommerce fraud has increased 15% year over year, with estimated losses from chargebacks alone reaching nearly $55 billion. The rise of AI has accelerated this trend: fraudulent actors now use generative AI to create fake identities, steal customer card data, and run large-scale card testing operations. What once required specialized skills can now be automated, allowing bad actors to launch coordinated attacks that are harder to detect.
Many businesses tell us that their existing fraud solution can’t adapt to this evolution. When new fraud vectors appear, businesses face a difficult choice: invest months of engineering resources to customize their existing systems, adopt specialized solutions for each new fraud vector, or hire additional fraud analysts.
Global businesses spanning dozens of industries have chosen Stripe Radar to combat these threats. Explore how six of those enterprises—each with very different use cases—are all using Radar’s AI-powered fraud prevention tools to prevent losses, increase revenue, and save time.
How Samsonite achieved a 98% payment success rate
Samsonite, a US-based luggage brand, is beloved by travelers worldwide for its lightweight yet durable products.
To strengthen its ties with customers, Samsonite’s Japanese subsidiary has been working to improve its CRM and bring certain operations back in-house to pursue a direct-to-consumer business model. As a part of these initiatives, it also implemented 3D Secure 2.0.
After two or three months on 3D Secure 2.0, Samsonite Japan saw a sudden increase in failed payments and several inquiries from customers who had difficulty making a purchase.
Solution
Samsonite implemented Radar, an advanced fraud detection system that uses AI models trained across millions of global transactions to help block fraudulent transactions. Radar’s customizable rules make it possible to apply 3D Secure 2.0 selectively to high-risk payments.
Upon adopting Stripe, the payment success rate rose to 98%. Samsonite was even able to get through the busy Black Friday sales without any increase in fraudulent payments. Stripe’s Authorization Boost was a key contributor: it improves payment success rates by 2.2%, on average, by retrying failed payments and making several attempts to each card issuer.
How GitHub saved four to five hours per week addressing fraud
GitHub Sponsors enables organizations and businesses to make one-time or recurring payments to developers working on open source projects to maintain, secure, and innovate the software that runs the world.
As the core open source funding platform, GitHub Sponsors needed to maintain high levels of security and trust. In particular, the platform needed the tools to identify and prevent malicious activities such as credit card fraud.
Solution
To manage fraud risk, GitHub deployed Radar, which uses AI to detect and block fraudulent transactions. GitHub also recently turned to Smart Disputes, a new AI-powered solution from Stripe that automates the chargeback response process by automatically generating and submitting evidence to counter disputes.
Prior to the use of Smart Disputes, GitHub Sponsors would review disputes manually. Tracking down evidence for some disputes was time-consuming and strained the team. Disputes were rarely if ever contested due to the time involved. With Smart Disputes, GitHub Sponsors saves four to five hours of work per week.
In the first months since we introduced Smart Disputes, we’ve seen promising momentum in our ability to shift resources to other priorities, without the concern of disputes expiring before we can [counter them].”
How Kickstarter prevented $9.5 million in fraudulent charges
Kickstarter is the premier crowdfunding platform for creative projects. It brings together creators and a community of potential supporters to raise money for projects in almost any medium—from art, music, books, and games to fashion, technology, and design.
Kickstarter’s recent priorities included ensuring that its system supports ongoing expansion, allowing the company to quickly enter new markets and adapt the platform for local regulations regarding customer identity verification and payment security.
Managing fraud across the entire platform is another key challenge, given that each Kickstarter project attracts different cohorts of backers using a varied mix of payment methods in multiple countries. Each of those payment methods has different user verification methods and ways that bad actors can exploit them to commit fraud, making it difficult to manage fraud risk with a single approach.
Solution
To help manage payment fraud, Kickstarter adopted Radar, which uses AI trained on the billions of transactions processed on the Stripe network, to analyze data for shifting fraud patterns and potentially risky transactions. Radar automatically blocks transactions deemed the highest risk and sends notifications to Kickstarter’s internal trust and safety team, which can then analyze those transactions alongside signals from other fraud monitoring efforts to either remediate issues promptly or refine its overall techniques for identifying risks such as insincere pledging or account takeovers.
Stripe and Radar automatically blocked $9.5 million in fraudulent charges that likely would have ended in disputes.
Because we were early adopters of Stripe, we’ve seen Stripe’s vision of what it can provide its customers change over time. Stripe has grown from working as payments facilitator to offering a robust suite of financial services to help businesses grow.”
How FreshBooks blocked more than 300 fraudulent accounts from onboarding in 3 months
More than 30 million small businesses have used FreshBooks accounting software, built for small businesses and accountants. To continue to meet customers’ evolving needs, FreshBooks expanded its payment capabilities with an embedded payment solution.
As FreshBooks experienced significant growth over the years, so did many of the businesses it served. By 2023, FreshBooks’ payment needs had changed, and it wanted to offer an end-to-end payment experience with easier onboarding, reduced friction, more control of customers’ payment journey, and the opportunity to offer more financial services going forward. FreshBooks also wanted to ensure its new payment solution could help its customers mitigate fraud even as they scaled their businesses.
Results
FreshBooks adopted Radar for platforms, addressing a key business challenge. Traditionally, separate merchant underwriting and transaction monitoring processes made it hard to quickly spot unusual payment activity. Radar for platforms links these processes, enabling more accurate and timely fraud detection across both merchants and transactions while reducing false positives. With Radar for platforms, FreshBooks is now able to use dynamic, risk-based decisioning that provides a real-time view of its portfolio health daily.
[Radar] has significantly increased the efficiency of our risk team to focus efforts where manual intervention is truly needed, and has allowed us to block more than 300 fraudulent accounts from onboarding onto our platform in just 3 months.”
How La Redoute reduced fraud risk and achieved a 98% authorization rate
Operating for nearly 200 years, La Redoute is a leading European retailer of home furnishings and clothing.
In 2022, company leaders determined they needed to replace La Redoute’s web of disparate legacy payment systems with a single global solution. The company’s existing tech stack, with different solutions for different countries, was inefficient and burdensome to manage.
In modernizing its payments technology, La Redoute also needed a payments provider that would help it meet Strong Customer Authentication (SCA), a European regulatory requirement aimed at reducing fraud and making online payments more secure. The company needed comprehensive fraud protection that would block fraud while keeping authorization rates high.
Solution
La Redoute chose Stripe to replace its fragmented payments stack. For global fraud protection, La Redoute used Radar, an AI-powered solution that trains on billions of data points to detect and block fraud automatically. For additional fraud protection and to comply with SCA requirements, La Redoute relies on Stripe Payments, which supports 3D Secure as an extra security measure that further reduces fraud while maintaining frictionless payments authorization.
Radar and support for 3DS have helped La Redoute achieve a secure checkout that automatically detects fraud while also optimizing for a smooth checkout experience. La Redoute’s Stripe integration has led to more 3DS exemptions, resulting in frictionless rates above 80% in every country. With Radar and Payments in place, La Redoute’s authorization rates exceed 98%.
We’ve used Stripe’s machine learning–based authentication engine to offer frictionless 3DS and exemption flows. It not only reduces fraud risk but genuinely elevates our customers’ shopping experience. With Stripe, we have peace of mind and our customers do, too.”
How Oasis Hotels reduced fraud by 90%
Oasis Hotels operates hotels and all-inclusive resorts in tourist destinations including Cancun and Tulum, Mexico, serving international guests via an online booking platform.
The Cancun-based company was grappling with a 6% fraudulent dispute rate on transactions, well above industry standards. Fraud didn’t just cause significant revenue loss; it also required substantial administrative resources, as staff struggled to handle disputes and reconciliations manually. The problem was compounded by the fact that Oasis’s existing payment system offered limited visibility into fraud patterns.
The challenges made it clear that Oasis needed more sophisticated payment and fraud prevention to support its growing business.
Solution
In 2023, Oasis Hotels chose Stripe as its payments partner based on Stripe’s reputation for reliability, advanced fraud prevention tools, and ease of integration. The company’s first priority was tackling its fraud challenges with Radar for Fraud Teams.
Oasis worked closely with Stripe’s team to develop custom fraud rules that addressed its specific vulnerabilities. Oasis identified that many fraudulent transactions showed a discrepancy between the name on a reservation and the name on the card used for payment. The team implemented a custom rule that automatically compared these names and applied 3D Secure authentication when they didn’t match, which adds an additional layer of verification before a payment is processed.
Oasis also relied on Radar’s risk scores, which represent the level of fraud risk associated with a transaction—the higher the score, the greater the risk. Using the custom rules capabilities in Radar for Fraud Teams—which allow users to single out variables such as the number of previous disputes associated with a specific card number or IP address—Oasis was able to implement rules that used 3DS to automatically block cardholders who had a tendency to dispute past transactions.
Thanks to custom rules and other optimizations in Radar for Fraud Teams, Oasis’s dispute rate plummeted 90%, from 6% to less than 1%, in just 6 months.
[Radar for Fraud Teams has] saved many hours each week for Oasis administrative staff. Dispute and refund management and reconciliation are done more efficiently now.”
How Stripe can help
With Radar, you can identify and prevent fraud in real time with AI, powered by Stripe’s global data. Radar is built into Stripe and seamlessly integrates with the full Stripe platform, allowing you to get started right away with zero code required. And now, you can get access to Radar’s risk scores even if you use an external payments provider to process transactions. We plan to make more of Radar’s capabilities available off-Stripe soon.
With Radar, you can:
- Automatically detect and block fraud: Radar reduces fraud using AI that trains on data across millions of global companies. Our scale enables us to detect and automatically block true fraud more accurately to save you money from fraud losses. We’ve been able to reduce dispute rates for Radar users by 17% last year.
- Reduce card testing attacks: Thanks to our Payments Foundation Model, an industry-first AI model trained on tens of billions of transactions, our detection rate for attacks on large users significantly increased from 59% to 97%.
- Save time and money on disputes: Unify disputes management from end to end with Radar. You can proactively refund transactions to prevent disputes before they occur with Smart Refunds, reduce your dispute rate to avoid card brand monitoring programs with dispute prevention, and use Stripe’s AI to tailor and submit evidence for eligible disputes on your behalf with Smart Disputes.
- Dynamically apply two-factor authentication: Stripe can handle European SCA requirements and dynamically apply authentication, such as 3DS, when required by the cardholder’s bank or when fraud is suspected.
- Manage your platform’s risk end to end: Identify fraudulent connected accounts, set custom account-level rules, and intervene on suspicious transactions with Radar for platforms.
- Create rules to customize fraud: Using Radar for Fraud Teams, you can create custom rules to manage how your business handles incoming payments, blocking any that you would consider suspicious or placing them in review.
To learn more about how Stripe can help your business fight fraud and disputes, contact us or sign up for an account.