You’re a worldly, 21st century business. You keep up with your customers by offering real-time purchasing, allowing customers to exchange virtual cash, and encourage easy checkout by app or website. You’re doing everything you can to be competitive and buzz-worthy in this digital minefield of e- and m-commerce.
But because you’re reducing friction and encouraging quick transactions, you might be inadvertently opening yourself up to malicious users. From something as “benign” as coupon or referral abuse to straight-up credit card fraud, websites and apps are seeing it all. Even the bad behavior that seems relatively harmless – like spammy content or fake accounts – ends up damaging your business’ reputation and your customers’ experience.
What are the characteristics that attract fraudsters to your site? And how can you stay competitive while giving criminals the stiff arm? We’ve had four years of helping businesses of all sizes and across industries prevent, and we’ve observed 5 magnets that draw fraudsters to merchant sites:
1. Real-time order fulfillment
The on-demand economy is growing rapidly. But limiting the window to manually review orders makes fraud management unscalable – there’s no way that a business like Instacart can check every order that comes in and ensure that the delivery arrives to its purchaser within hours. This tightened timeline means that fraudsters can swoop in and capitalize on an on-demand business’ need to fulfill now and check for legitimacy later.
2. Marketplaces and user-generated content
Match.com would be nothing without its users. Airbnb would have nothing to offer without its homeowners and renters. Businesses that rely on user accounts and facilitate exchanges between users are susceptible to account abuse, where fraudsters try to scam legitimate users or dilute good content with spam. This bad behavior can spoil the experience for everyone else.
Stiff Arm courtesy of Eugene Kim, found on Flickr
3. Virtual cash payments
Maybe you’re a crowdfunding site, or you deal in remittances for overseas friends and family. Perhaps you buy and sell e-gift cards or bitcoins? Regardless of the business, you deal in virtual cash. Fraudsters love businesses that deal in virtual cash because it’s easy to get in and use scam purchases to get the digital money, or buy bitcoins and gift cards with stolen credit card numbers. Users that exchange virtual payments expect quick delivery of funds, so by the time the credit card fraud is reported or the gift card is discovered to be empty, it’s too late.
4. Referral programs and coupon codes
Referral programs are a great way to reward your loyal and evangelist customers, and coupon codes are an easy means of welcoming new customers or welcoming back old ones. But without proper oversight, either of these promotions can be abused, costing your business countless hundreds or thousands of dollars. Are you sure that every referral is a true measure of your business growth, or is someone scamming your system?
5. Online travel and bookings
Where do e-commerce, m-commerce, on-demand and real time transactions, referral fraud, and virtual cash all collide? In the online travel space. Fraudsters flourish on travel sites and apps, since transactions often cross geographical, financial, and social borders, all at the speed of light.
Do you recognize your business in the descriptions above? Good news! Large-scale machine learning can help you predict who the bad users are and stop them fast. Online and large-scale machine learning offers you the world of known users – good and bad – so you can easily identify those known fraudsters and separate them from the known legitimate shoppers. Looking to expand your business into a new market? Machine learning can help. Hoping to grow your user base and reduce checkout friction? Ding ding! Machine learning is a great tool.
We at Sift Science are passionate about harnessing the power of machine learning to help businesses operate more efficiently and scale with confidence. Check out our capabilities by visiting our website and checking out our solutions. We’d love to answer any questions that you might have, so tweet us or drop us a line via our chat widget on https://siftscience.com.