More e-commerce fraud, customers to be careful

E-commerce fraud is becoming more prevalent, says US internet payments technology company Stripe in a new report.

Fraudsters repeat online purchases at the same businesses 10 times more quickly than actual cardholders, says the report, which reveals new patterns to help e-commerce companies combat fraudulent activity during the holiday shopping season.

With chip-enabled credit cards making brick-and-mortar shopping safer, criminals are turning their attention to online stores. Unlike physical stores, online businesses have to pay the associated costs of fraudulent orders. On average, every $1 of fraudulent orders costs an online business an extra $2.62.

Stripe looked across a year’s worth of data to seek out fraudulent behaviour patterns by country, time of day, industry and other factors. Insights to emerge include:

• Fraud rates based on the country where the credit card is issued vary dramatically, by a factor of two or three

• In Singapore, fraudulent transactions are significantly larger than normal transactions

• The highest online fraud rates occur during days and times when many people are not shopping, such as Christmas Day or late at night (for example, for US businesses, fraud rates as a percentage of overall traffic increase in the summer and in late December, but not on heavy shopping days like Black Friday)

• Fraudsters give themselves away by making rapid additional charges at the same businesses on the same credit card, initiating repeat purchases 10 times more quickly than actual cardholders

• • Fraudsters prefer products that can be delivered to locations like public buildings or parks and can be obtained quickly before transactions are invalidated, which explains the prevalence of fraud among on-demand services as well as low-end consumer goods.

“While there are some consistent patterns to fraudster behaviour, such as their high-purchase velocity, their propensity to work late at night and their preference for cheap or immediately deliverable goods, we have found that the predictive strength of these patterns varies widely depending on the location of the business and the fraudster,” says Stripe engineering manager for payments intelligence Michael Manapat.

“Because of this, we recommend using anti-fraud tools based on machine learning from large amounts of data.”

Principal analyst Jordan McKee of 451 Research says it is crucial for online businesses to have robust fraud defences, especially during the busiest shopping season of the year.

“Because online fraud is highly complex and increasingly global, merchants should consider outsourcing fraud tooling to trusted third-party providers that have access to large, robust data sources. The most effective providers draw on global data sets from hundreds of thousands of other businesses to train their machine-learning algorithms and identify even subtle fraud patterns.”

For its report, Stripe examined transaction data across hundreds of thousands of its customers across 25 countries. Stripe works in more than 25 countries to allow both individuals and businesses to accept payments over the internet.