Nonprofits Are Ground Zero for Fraudsters to Test CNP Fraud
Nonprofits are certainly not the first industry that comes to mind when you think of credit card fraud. However, in the world of card not present (CNP) fraud, nonprofits are ground zero for fraudsters to test stolen credit cards.
Nonprofit organizations’ donation pages are the focal point for fraudsters. Donation pages of a nonprofit’s site are designed to create the least amount of resistance for potential donors to contribute. In comparison, online retailers present several fields to complete transactions and often require users to establish an account, fill out billing and shipping addresses, and input an email address and a phone number.
For fraudsters, a donation page provides an opportunity to test the validity of a credit card. Fraudsters test those cards in small and often random amounts — think tiny donations, like $1.63. Once that small donation goes through without a hitch or a red flag, the fraudster knows that the card is good to use (at least for the time being) and will either sell the card or go on to make large purchases using that stolen card.
While this may sound innocent enough because of the small transaction amount, the numbers tell a different story. During a recent webinar presented by Kount, Kamran Razvan Ph.D., CEO of Click & Pledge shared a story where his company stopped approximately 130,000 transactions during a 20-minute period. Click & Pledge’s use of machine learning within their fraud solution recognized that all the donations were originating in Brazil and were fraudulent. Razvan shared “The sheer volume of transactions that hit our site in that short of a period was similar to a DDoS attack.”
Machine learning allows nonprofits (and others) to contextualize an enormous amount of transactional data to make informed and confident decisions. Machine learning analysis of a group of transactions allows nonprofits to see patterns in the data. This data is critical to understanding the use and validity of credit cards in relation to specific patterns that are associated with fraud and define thresholds to approve, decline or flag for further review. The use of a machine learning enterprise fraud solution allows nonprofits to thwart attacks before theydamagethe overall brand and receive chargebacks, associated fines and/or troubles with TC-40 reports.
Machine learning empowers decision makers with the ability to access data, understand its meaning and make informed decisions to stop fraud before it impacts the businesses’ bottom line and the overall brand. Machine learning is the way that the industry is moving to stay ahead of criminals that are looking to commit fraud.
Customers that are evaluating fraud solutions should be able to:
- Access high quality data collection and creation.
- Use feature engineering that harnesses data to create new and informative decisions.
- Apply domain expertise specifically focused on fraud.
- Incorporate patented unsupervised and supervised machine learning.
- Apply human intervention and customization when needed.
