Real-time, instant payments are praised lately for being more convenient for the consumer to use, and very affordable for the merchant to accept these payment methods. But how secure are these transactions since there is a shorter time to review? Have fraudsters explored any loopholes so far?
While real-time payments come with a variety of benefits, they also bring some notable drawbacks, particularly when it comes to security and risk measures. What merchants need to be aware of is that although instant payments can provide immediate customer satisfaction, they can also be responsible for instant fraud. With instant payments, the merchant has to decide whether to accept the transaction in real time, and once they make the decision, they can’t undo it. Unlike other types of fraud, money recovery for instant payment fraud is impossible. To accommodate instant payments while keeping fraudsters at bay, merchants need to use advanced machine learning to vet transactions in real time.
What about chargebacks and friendly fraud? Can these issues be disputed in the same manner as when a card transaction is involved?
Friendly fraud can often be a misunderstanding, and consumers simply don’t remember making a purchase or someone else who is an authorised user of their card makes the purchase and they are unaware. It’s typical for a consumer who sees a charge on their credit card statement that they don’t recognise to dispute it, even if it’s a legitimate purchase that they made. If the descriptor that shows up on their bank statement is completely different from your company name, that’s an immediate red flag for consumers and will likely lead to increased levels of these sorts of incidents.
To prevent friendly fraud, it’s important to be clear and transparent. Be sure to include your business or store name as part of the descriptor so your customers will be able to easily identify where the charge is coming from and avoid any surprises when they look through their bank statement.
Chargebacks, on the other hand, are more likely to be exploited by fraudsters for personal gain. If the dispute is won by the customer, not only does the merchant lose the revenue from that sale, but they also lose the merchandise that was delivered to the fraudster. Moreover, if a business incurs a large number of chargebacks, the credit card company could blacklist the merchant altogether or subject the business to increased card processing fees.
How can machine learning be leveraged to prevent fraud in this space? Does a combination with rules technology work as well?
Fraudsters don’t operate from a single location – they’re all over the world, so your machine learning models need to have a global outlook. This is particularly crucial for CNP fraud with indirect linkage, since there is no clear sign for merchants to watch for.
Data from our recent Global Card-Not-Present (CNP) Fraud Report found that fraudulent transactions with indirect linkage are on the rise with the percentage of overall fraud with indirect linkage increasing steadily quarter-by-quarter through all of 2020. And to make matters even more difficult, the value of fraudulent transactions with indirect linkage is generally higher than those with direct linkage, making it an even more expensive and complicated problem for merchants to deal with.
With the AI advancements over the past few years, there are a variety of ways merchants can tackle fraud with machine learning. Sophisticated machine learning models can identify connections between disparate transactional data points to identify potential fraud in real time, which allows merchants to make an instant decision on whether to accept or reject a transaction. While machine learning models can effectively prevent CNP fraud, it’s important to consider the data the models are trained on when evaluating different solutions. Machine learning models are only as good as the data that powers them, so merchants should aim for models that have been trained on several years of transactional and global data. The historical data ensures machine learning models understand how fraud has evolved, and the global data ensures these models can identify fraud regardless of where it comes from.
What industries do you see as being more affected by fraud and why? Do you see any disruptive fraud trends emerging that are likely to significantly impact the ecommerce industry?
Fraud is sweeping across every sector of our economy and the airline industry is no exception. With an estimated USD 1 billion in annual losses in the US alone, the cost of airline fraud could force airlines to raise their booking rates, which is a major concern for everyone. Similar to ecommerce and retail practices, the barriers to purchasing an airline ticket are exceptionally low, which is one of the primary reasons why fraudsters target this industry. Just like purchasing a new pair of shoes, it’s not uncommon for consumers to purchase airline tickets while they’re on the go, making it difficult to accurately verify their IP address. With the landscape of digital payment solutions constantly evolving, cybercriminals are finding new ways to exploit the system, bringing to light a whole new set of challenges for merchants across a range of industries.
How can Vesta support businesses in securing online payment transactions and reducing decline rates?
About Tan Truong
Tan Truong builds and leads Vesta’s technology, product, and operations teams to create a high-performance, innovative culture. With 15+ years of IT implementation under his belt, Tan develops Vesta’s data science and machine learning capabilities to move beyond fraud detection and into fraud recognition and prevention as we approach a digital-first economy.
About Vesta
Every day we send out a free e-mail with the most important headlines of the last 24 hours.
Subscribe now