Customer experience (CX) is increasingly critical for retailers, and false declines leading to declined transactions can be a major CX blocker. What should retailers do to reduce the number of false declines to improve CX?

SM: Today’s consumers have high expectations when it comes to the online shopping experience; one negative experience – whether falling victim to fraud and having their information stolen, or having a valid purchase rejected – can turn them away for good.

The latter is known as a false decline, and is one of the biggest and most common pain-points for merchants. When a legitimate payment is declined due to suspected fraudulent activity, this has a direct impact on not just the merchant’s revenue, but also on its customer’s experience.

While it’s very difficult to accurately identify what percentage of declined transactions are truly fraudulent, it’s estimated that false declines make up over half of all declined orders. The higher the price-point of the product, the higher the merchant’s decline rate will typically be.

Preventing false declines is not complicated, and does not have to compromise the customer experience. Vesta recommends three actionable recommendations to help merchants fight this, and prevent it from impacting their revenue and hurting the customer experience:

  • Only decline payments based on data, not on assumptions: Using lots of rules tends to result in a high number of false declines – meaning you’re likely to block a lot of genuine customers. For example, high-value orders and orders from high-risk locations are more likely to be fraudulent. But if you enable a rule which blocks all transactions over $300 or every payment from a risky region, you’ll lose out on lots of genuine customers’ business too.
  • Implement professional fraud prevention software: it is no longer practical to rely on manual intervention and rule-based technology to catch fraudulent transactions. The thresholds for fraudulent behavior can change over time – for instance, if your prices change, the average order value can go up, and that means orders over your earlier limit (e.g. $1,000) become the norm. Your earlier rules can become invalid if they are not updated appropriately and timely. Rules are also based on absolute yes/no answers, and do not allow merchants to adjust the outcome or judge where a payment sits on the risk scale.
  • Leverage Progressive Machine Learning Fraud / Approval Guarantee Technology: These programs are highly accurate and perform exponentially faster than a human could, and constantly calibrate to keep up to date. With automated fraud detection, merchants are able to reduce overhead costs while simultaneously increasing their transaction approval rates. 

Vesta offers end-to-end protection that is fully scalable based on each merchant’s needs. With the threat of payment fraud accelerating faster than ever, it is important for merchants to stay up-to-date with the latest fraud prevention trends so they know how to best protect their business. 

How does machine learning help Vesta learn more about fraud, and how has this set Vesta apart from competitors in terms of both merchant and customer experience?

SM: Vesta is an established global leader in fraud prevention for online purchases. Using machine learning backed by 25 years of transactional data history, Vesta increases approvals of legitimate sales for its customers, while eliminating chargebacks and other forms of digital fraud.  Expanding into Southeast Asia, we remain committed towards enabling growth while managing risks for the region’s businesses and their revenues. 

To meet the challenge of fraud scenarios like ATO or false declines, we employ a uniquely orchestrated approach that combines biometric evaluations with machine learning to discover and prevent ATO fraud before any unauthorized transaction can occur. 

Additionally, using our graph link database, we are able to observe every transaction ever made on a site – from who created the order, to how it was paid and how it was delivered. This advanced feature draws connections between 2 trillion data points and helps us connect the dots in real-time, analyzing between fraudster networks vs. good networks.

Our models also constantly adapt to new threats on a global scale, drawing data from millions of transactions every minute. All this real-time data allows us to make an accurate risk assessment in milliseconds, effectively preventing fraud while reducing false declines.

On top of our fraud prevention capabilities, our ‘Payment Guarantee’ solution makes the decision whether to approve or decline a transaction in less than a second without adding any friction to the customer experience.

Once a transaction is approved, the liability of fraud is taken off a merchant’s plate and is shifted to Vesta – should the transaction turn out to be a fraud, Vesta covers it immediately, with zero cost to the merchant. 

This sets us apart, as fraud generally comes with a multi-dimensional cost – from the refund of the charge to the cardholder (the victim of the theft), to the friction that was unnecessarily imposed on the customer.

It is this ‘cost’ of fraud that we hope to entirely eliminate from merchants as far as possible.