JPMorgan Payments has introduced an AI-driven Account Confidence Score (ACS) to help corporate treasurers assess fraud risks before processing payments. Using insights from more than 15 billion JPMorgan Payments transactions, the ACS evaluates beneficiary accounts based on multiple criteria, including account age, payment history, geographical data, fraud records, transaction frequency, and inter-account relationships.
The score, generated by a machine learning model, ranges from 0 to 1,000, with higher numbers indicating stronger confidence in the legitimacy of the recipient account. Clients will receive a simple Red, Amber, or Green indicator linked to the score, guiding them on the potential risk level and offering actionable steps to mitigate threats.
JPMorgan says the ACS is designed to help prevent various payment fraud types such as business email compromise, payroll fraud, invoice scams, and account takeovers. Greg Hodges, head of trust and safety at JPMorgan Payments, highlighted the tool’s significance, stating, “The Account Confidence Score underscores our commitment to equipping our clients with the right tools and solutions to navigate the ever-evolving complexities of the digital payments landscape, especially as businesses face unprecedented fraud threats.”
The ACS represents JPMorgan’s broader push to use advanced data science and AI to enhance trust and safety in corporate finance, offering real-time risk insights to reduce financial vulnerabilities in a rapidly digitising ecosystem.