The company on Tuesday (March 31) announced an enhancement to its real-time decisioning (RTD) offering with “an AI-powered risk score that analyzes transaction risk levels at the point of the authorization decision.”
According to a news release, the new capabilities help Marqeta customers make smarter, data-driven risk assessments to prevent payment fraud and reduce false declines.
The release cites projections that global payment fraud is expected to jump 153% by the end of the decade, highlighting the need for fraud detection models that can detect new fraud patterns and stay on top of emerging threats.
Marqeta says it addresses this challenge by melding its RTD authorization rules with the predictive power of machine learning in order to continuously spot new fraud patterns and fend off emerging threats.
“Today’s fraud threats are evolving faster than ever, requiring businesses to keep pace as they scale their card programs,” said Anthony Peculic, Marqeta’s interim chief product officer.
We’d love to be your preferred source for news.
Please add us to your preferred sources list so our news, data and interviews show up in your feed. Thanks!
Advertisement: Scroll to Continue
“By embedding AI-powered controls and advanced machine learning into the authorization process, we enable customers to expand confidently while also strengthening their fraud defense as they scale.”
In other fraud prevention news, PYMNTS wrote Tuesday about new research that examines the rising threat of bots.
That research shows that 56.3% of companies are now dealing with threats tied to bots or agents, 58.6% struggle with bot-driven fraud, and 52.3% say bot traffic picked up over the last 12 months.
Financial services firms are feeling this strain most acutely: 60.6% said they’ve witnessed increased bot traffic, the largest share of any industry. Companies also lose an average 3.1% of annual revenue due identity verification gaps — a yearly collective hit of around $95 billion across the companies surveyed.
“The most telling data point may be the confidence gap. Nearly all respondents—96.3%—say they are confident in their ability to detect harmful bots. Yet nine in 10 report challenges from harmful bot traffic,” PYMNTS wrote.
“That mismatch helps explain why ‘good enough’ identity stacks are becoming a strategic liability. The companies that appear to be coping best are moving beyond fragmented checks toward integrated, global identity platforms.”
The research also showed that nearly 79% of companies using global identity platforms say vendor quality and reliability drive confidence in their verification procedures, while 65.6% report lower digital transaction decline rates and 62.5% saw lower false declines over the last year.
Add as Preferred Source
