Solutions overview
Harness the power of your data
Support and investigations
Support services for Ravelin
Online payment fraud
Account security
Policyabuse
Marketplace fraud
3DSecure
Resource Zone
Deep dives on fraud & payments topics
API & developer docs
APIs, glossary, guides, libraries and SDKs
Global Payment Regulation Map
Track PSD2 & more with a full report
Blog
The latest fraud & payments updates
Insights
In-depth guides to fraud, payments & security
About Ravelin
Discover the story about Ravelin
Careers
Join our dynamic team
Customers
Read more about our happy customers
Press
Get the latest Ravelin news
Support & investigations
Accept more payments securely
Protect your customer accounts
Policy abuse
Stop policy abuse to protect your bottom line
Ravelin for marketplace fraud
3D Secure
Ravelin 3DS & SDKs
Resource zone
Global Payment regulation map
Read more about our happy custmomers
Blog / Fraud Analytics
Online marketplaces are vulnerable to fraud from suppliers as well as customers. Learn how to identify supplier fraud and why it needs a different approach to customer fraud.
Share this article:
Supplier fraud is an increasing concern for on-demand marketplaces, such as couriers/delivery services and ridesharing apps. Fraudulent behavior from suppliers can have as high a cost as card-not-present (CNP) payment fraud, but it’s often more challenging to spot as it rarely results in chargebacks.
Supplier fraud also has a negative impact on the user experience for genuine customers. Longer wait times, lost orders and higher fees cause customers to lose trust in a business. It also puts greater pressure on legitimate suppliers to remain competitive.
Marketplaces connect suppliers with customers. Supplier fraud affects marketplaces where the customer selects a specific supplier, as well as marketplaces where the customer selects a service instead of a specific supplier.
Exposure to supplier fraud is often highest during expansion, when a marketplace onboards new suppliers quickly and offers generous incentives to attract customers. There are many other factors that impact supplier fraud rates eg. products/services offered, onboarding processes and business strategy.
Suppliers typically turn to fraud when they see an opportunity to boost their earnings. In some cases, suppliers might seek to improve their ranking within the marketplace, or launder money from CNP payment fraud.
Low-value orders from fake customer accounts
A supplier creates fake customer accounts to place orders that are lower in value than the fee they are paid as a supplier - for example, a courier may place orders for low-value items (eg. a drink) to receive the delivery fee.
Order cancellation
A supplier uses a fake account to place an order with cash delivery, in this scenario the marketplace advances the restaurant the payment. Once they receive the payment, the restaurant cancels the order and keeps the payment.
Collusion between a customer and supplier
Using a ridesharing marketplace as an example - a passenger and driver pre-arrange a trip using a stolen credit card. In return for accepting the fare, the driver will receive a large fee.
Referral schemes and promotions
Suppliers may create fake customer accounts to unlock rewards - eg. discounts for new customers, referral schemes or a bonus based on the number of orders completed over a period of time.
It’s important to emphasise that the methods used in supplier fraud are very different from methods used by professional fraudsters who commit typical CNP fraud.
With online payment fraud, the typical fraudster uses stolen credentials to make orders, sometimes using lists containing hundreds of accounts or credit card details. Supplier fraud is far more opportunistic. The majority of the time, suppliers only occasionally commit fraud based on specific circumstances.
Why is this important? When a user is caught committing CNP fraud they are usually blocked from making any future orders. However, a marketplace needs suppliers to function, and if it blocks every supplier who does something slightly fraudy it may not be able to fulfill genuine customer orders. Therefore instead of permanently blocking suppliers, we prevent specific negative behavior.
To help marketplaces combat this problem, we offer an anomaly detection model to look at the supplier history and identify patterns of behavior that indicate fraud. As well as the supplier, we also look at the combined risk of the supplier, customer and the order itself.
This means the marketplace can prevent the potentially fraudulent suppliers from being matched with high-risk customers/orders. The supplier is still able to fulfill low-risk orders, so if there are any false positives it doesn’t prevent them from earning. Also, the dynamic approach of our anomaly detection model means that if the supplier's behavior improves, they are not permanently penalized. We recognize suppliers are not inherently bad and typically have more good, fulfilled orders and fewer fraudulent orders.
We also look into networks where suppliers are working together, potentially sharing a group of fake customer accounts or working with the same colluding customers. In this sense, networks allow us to identify potentially fraudulent suppliers that have just emerged and therefore hadn't been identified by our machine learning model.
Shared properties between a supplier and customer (or between customers)
eg. Name, surname, phone number, address, device.
Similarity between a supplier and customer (or between different customers)
Look out for similar names, contact numbers or emails, eg. one character change.
Supplier receiving repeated orders from the same customers
Nearly always suspicious for commoditized suppliers (eg. couriers or drivers). With differentiated suppliers (eg. restaurants) this is common and not a sign of fraud.
Also look for any suppliers receiving a higher than average proportion of:
If you want to learn more about how we can help you manage supplier fraud at Ravelin get in touch here.
Jessica Allen, Head of Content
Fraud prevention is a delicate balance between stopping fraud and maintaining good customer experiences. But what is the most effective way to measure this outcome?
Ravelin Technology, Writer
Blog / Machine Learning
Online payment fraud is one of the biggest threats facing grocery merchants. And it’s only gotten worse. How are fraudsters using the cost of living crisis to take advantage of your business?
There’s a new fraud threat on the rise – and it’s your customers. First-party fraud is infamously tricky to catch and a huge revenue risk. How can you detect and deter criminal behavior in your customer base?