One significant concern with faster payments is the risk of increased fraud, but artificial intelligence (AI) can help mitigate these risks.

A Study from BIS and BOE Highlights AI’s Fraud Detection Capabilities

A study conducted by the Bank for International Settlements (BIS) and the Bank of England examined AI’s effectiveness in identifying sophisticated fraud activities. The research, titled Project Hertha, utilized simulated data based on millions of bank accounts and transactions to mimic real-time retail payments.

The results revealed that AI models outperform traditional fraud defenses by 26%. Specifically, AI successfully detected suspicious activity more effectively and uncovered 12% more fraudulent accounts than conventional methods.

AI’s Impact in Fraud Detection

According to a separate study from FIS, 78% of respondents report that artificial intelligence has improved their company’s fraud detection and risk management strategies. Nearly half of these business leaders plan to increase investment in AI over the next two years, intending to delegate more complex tasks to it.

The Double-Edged Sword: Agentic AI in Fraud Detection

Agentic AI, a powerful form of AI that can handle many tasks autonomously, offers significant potential for fraud prevention. However, experts often view agentic AI as a dual-edged sword. While tech professionals recognize its growing threat to security, 96% still intend to expand its use in the coming year.

Challenges and Limitations

Cybercriminals have already leveraged both generative and agentic AI on a large scale. They employ these technologies for various fraudulent activities, including deepfakes and ransomware attacks. Unlike organizations, cybercriminals are not bound by privacy or reputation concerns.

AI tools can make mistakes, either missing genuine fraud instances or generating false positives. As such, BIS recommends viewing AI as a complementary tool rather than a complete solution to fraud prevention. Organizations must continue innovating new approaches to counter the head start given to cybercriminals through their use of these technologies.

Conclusion

The integration of artificial intelligence in fraud detection presents both opportunities and challenges. While it shows promise, it is essential for organizations to remain vigilant and innovative to stay ahead of evolving fraudulent activities.