How Mastercard Stopped $13B in Fraud With Real-Time AI
Technovation with Peter High (CIO, CTO, CDO, CXO Interviews)Show Notes
Mastercard processes billions of transactions, and fraud doesn’t wait for rules-based systems to catch up. In this episode of Technovation, Peter High speaks with Nirav Mehta, Chief Technology Officer at Mastercard Services, about how the company uses AI to score transactions in the milliseconds between a card tap and approval, and what it takes to build that kind of infrastructure at scale.
Nirav leads engineering, analytics, and decisioning for Mastercard’s $14B Services business, which spans fraud prevention, threat intelligence, data commercialization, and emerging agentic commerce. He explains how Decision Intelligence Pro prevented roughly $13B in fraud in 2026 alone before the holiday season, why the company treats data unification as a use-case-first problem rather than an architecture mandate, and how agentic commerce today resembles the early web, competing standards, good intent, unresolved identity questions. He also makes the case that senior technology leaders need to stay hands-on, not just well-read.
Key Highlights:
Decision Intelligence Pro stopped approximately $13 billion in fraud in 2026 year-to-date by applying AI models in the milliseconds between card tap and transaction approval
Mastercard’s Data Commercialization Platform reduced location-data staleness from 8-10 weeks to hours and cut processing time from multiple weeks to under 10 minutes
Agentic commerce is still in early-standards chaos, Mehta compares it to the web in its first years, and Mastercard’s bet is that its payments trust transfers directly to machine-to-machine contexts
GenAI is compressing engineering team size: a two-person pod plus ten AI agents is already viable for smaller programs, and the scarce skill is now systems thinking, not coding ability
Mehta makes the case for hands-on experimentation over passive learning, logging 1-1.5 hours of personal vibe coding daily since December 2025
This episode is sponsored by Tines. Freedom to build. Complete security. No compromises. Learn more at tines.io
More from Technovation with Peter High (CIO, CTO, CDO, CXO Interviews)
AI layered onto a broken process doesn’t fix the process; it just runs it faster. Prakash Kota spent his first 18 months at UKG consolidating two legacy companies into unified CRM, ERP, and data systems before any AI conversation began. Now, as Chief Transformation Officer, he is shifting the question from “what tools can we deploy?” to “what outcome are we trying to reach?” That discipline extends to the customer funnel, where AI-assembled signals travel with a prospect through every handoff, and to sales reps, where an autonomous assistant pushes pre-meeting briefs before a rep has to ask, reclaiming the 40–50% of call-prep time currently spent on research.
The binding constraint on AI adoption is not access to tools. It is the organizational fear and mindset shift required to reimagine work entirely.
Healthcare has accumulated friction that patients have come to accept as normal. Novant Health’s Chief AI Officer is systematically dismantling it.
Most generative AI programs stall at the pilot stage. Zoetis reached 95% computer-based colleague adoption.
The next generation of technology giants may not be built in software. They may be built in factories.