Advanced analytics and biometrics are becoming central to enterprise anti-fraud programs. AI adoption and plans are up 300%.
Real-time fraud detection and prevention has long been the holy grail of enterprises. Technology has provided highly robust tools for fighting fraud for some time. Now, advanced analytics and artificial intelligence are moving things to a whole new level – even stopping fraud even before it happens.
See also: Business Leaders: High Hopes for Real-Time Payments
“Thanks to data science, fraud prevention technology has now made enormous strides,” observes Sophie Van Dessel of EURA NOVA, the Belgium-based IT consulting firm. “Applying algorithms that use historical data to detect anomalies and patterns, data scientists are able to discover a potentially fraudulent activity before it occurs… and act against it.”
Advanced analytics and biometrics are becoming central to anti-fraud programs across many enterprises, according to a survey of 1,055 executives by the Association of Certified Fraud Examiners and SAS. The study found 13% of organizations use AI and machine learning to detect and deter fraud, and another 25% plan to adopt these technologies in the next year or two – a 300% increase.
The most common technique employed in fraud prevention is biometrics – fingerprint, facial, or keystroke recognition – with more than one-quarter already using such techniques and another 16% expecting to employ biometrics within the next two years.
Blockchain/distributed ledger technology and robotics, including robotic process automation, are currently used less frequently than biometrics (9% of organizations for both categories). But a similar proportion of organizations expect to implement these technologies in the next two years.
The technology least likely to be adopted as part of anti-fraud programs: Virtual or augmented reality. Only 6% of organizations currently use this technology, and nearly two-thirds do not expect to do so.
By 2021, nearly three-quarters of organizations (72%) are projected to use automated monitoring, exception reporting, and anomaly detection. Similarly, about half of organizations anticipate employing predictive analytics/modeling (52%, up from 30%) and data visualization (47%; currently 35%).
