Advanced Fraud Solutions Develops AI That Learns from Fraudsters’ Tactics

Nov 10, 2025
Advanced Fraud Solutions has announced a new AI system that uses real-world fraudster methods to improve financial institution protection and reduce false positives in transaction monitoring.

Advanced Fraud Solutions has developed proprietary AI technology that uses real-world fraudster tactics to enhance fraud detection for financial institutions, announced in a press release. The system draws on nearly two decades of operational data and fraud prevention experience to identify complex schemes while minimizing false positives.

The AI combines the expertise of a head teller, fraud investigator, and risk manager into a single analytical engine. It assesses transactions in real time by recognizing patterns related to check fraud, ACH vulnerabilities, and criminal behavior. The approach allows legitimate transactions to proceed smoothly while improving accuracy in detecting fraudulent activity.

The technology is built on actual financial transaction data rather than synthetic datasets, enabling it to recognize advanced schemes such as altered payee fraud, account takeovers, and coordinated fraud rings. It also includes enhanced Account Owner Authentication features that streamline verification for new accounts and reduce manual review time.

AFS plans to integrate the AI capabilities into its existing product suite, including TrueChecks, TrueACH, and TrueWire. Beta testing with select financial institution partners is scheduled for 2026.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Finance AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Finance AI Weekly

Weekly newsletter about AI in finance. Covers AI-driven trading, fintech innovations, and data analytics transforming markets

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.