Technology continues to evolve at a breakneck pace, but so, too, have scamming techniques become increasingly sophisticated and at times indistinguishable from legitimate transactions with banks and other institutions.

That's why Dr. David R. Hardoon, CEO of Aboitiz Data Innovation and Senior Advisor for Data & AI at Union Bank of the Philippines asks: Can artificial intelligence (AI) provide a decisive edge in combating these deceptive practices? He explores this potential in his latest commentary.

Dr. Hardoon highlights the evolution of scamming techniques, from basic schemes to advanced, personalized attacks that can precisely mimic legitimate communications. He emphasizes that while traditional scam prevention methods—such as consumer education, alerts or warnings, and transaction monitoring—play crucial roles, they often fall short in the face of innovative and unregulated scammers.

"The first truth we need to embrace is that no matter how informed, educated or careful a person is they will remain subject to being manipulated. Scammers are artists and we are their canvas," Hardoon says.

He adds that traditional measures of transaction monitoring like topologies, which are manual rules which try to capture the characteristic properties and patterns associated with the respective scams, can lead to false positives, where legitimate transactions are flagged as suspicious, thus failing to effectively target actual scams.

Dr. Hardoon proposes a shift towards AI-driven solutions that could revolutionize scam prevention by detecting and predicting scam patterns with greater accuracy, and even prescience.

He explains, “AI is the ability to see things differently - a family of methodologies to find and generate patterns, including the irregularity of patterns. It holds the ability not only to detect these patterns but to potentially predict them in advance. The true win for AI is the ability to be behavior focused - anomaly detection coupled with the ability to look for the subtle changes in behavior that may indicate risk or distress."

He suggests a future where AI could offer "Minority Report"-like capabilities in scam detection.

"Imagine a world where scammers still try to manipulate victims but now even if they succeed the scammers are prevented from accessing and moving the funds because proactive predictive measures have identified the true intent of the receiving accounts or store-of-value."

This future could be closer than we think, with Hardoon pointing out that several organizations have implemented these solutions on a large scale, achieving a 90% true-positive rate. This indicates that 9 out of 10 accounts flagged in advance are confirmed as either bad actors or compromised accounts with a future intention to scam.

The potential of AI in scam prevention is vast, but Dr. Hardoon emphasizes that realizing this potential requires imagination and a willingness to move beyond traditional practices. "Can AI save us from the losing war with scammers? Perhaps," he concludes, "if we start using it."