Industry News Details

Mastercard execs: Care and feeding of machine learning models is key to success Posted on : Dec 22 - 2021

With over 2.5 billion consumer accounts, Mastercard connects nearly every financial institution in the world and generates almost 75 billion transactions a year. As a result, the company has built over decades a data warehouse that holds “one of the best datasets about commerce really anywhere in the world,” says Ed McLaughlin, president of operations and technology at Mastercard.  

And the company is putting that data to good use. The fastest growing part of Mastercard’s business today is the services it puts around commerce, says McLaughlin.

IDG’s Derek Hulitzky sat down with McLaughlin and Mark Kwapiszeski, president of shared components and security solutions at Mastercard, to discuss how the company turns anonymized and aggregated data into valuable business insights and their advice for getting the best results out of machine learning models.

Following are edited excerpts of their conversation. To hear directly from McLaughlin and Kwapiszeski and get additional insights, watch the full video embedded below.

Derek Hulitzky:  Mastercard’s Decision Management Platform won our CIO 100 award in 2020.  And it uses AI and data for fraud detection. Can you tell us more about the platform?

Mark Kwapiszeski:   We use it for several purposes, primarily in our fraud products for creating things like fraud scores on transactions.  But what’s really exciting about the platform is just the size and scale and scope of what it does.  It’s built on about 900 commodity servers and it processes about 1.2 billion transactions per day at a rate of about 65,000 transactions per second, all of which it does in about 50 milliseconds per transaction.

It uses a lot of different AI technologies and techniques; it uses about 13 different algorithms, including things like neural networks, case-based reasoning, and machine learning.  But it’s not just running one model at a time.  We’ve actually built layers, where it can run multiple models at the same time, so that it can analyze all sorts of different variables within that transaction.

Derek Hulitzky: You’ve described how your analytics models aren’t static, and that you continuously monitor them to understand what’s happening with a transaction and why it happened.  Can you describe what you mean by that?

Mark Kwapiszeski:   When you consider every transaction that we see, every interaction, it could be fraud or it could be a mom trying to buy medicine for their child.  Every transaction matters.  So, we always have to know not only what happened, but the why behind what had happened. View more