How Mastercard is Using Artificial Intelligence To Get Rid Of Fraud Practices?

By Jyoti Nigania |Email | Jan 7, 2019 | 3585 Views

Having a card transaction declined at the checkout can be a frustrating and embarrassing occurrence. So much so that it can seriously damage brand loyalty according to research by Mastercard, a third of us have withdrawn our custom from a retailer due to our cards being refused.

Often this is due to the transaction being incorrectly flagged as fraudulent in some way the algorithms which make the call on whether a payment is valid to have erred on the side of caution, and sometimes they get it wrong. Aside from the inconvenience, it causes us, the cost to businesses and the wider economy of these false declines is around $118 billion an amount 13 times higher than the cost of actual card fraud.

But fear not because, once again, AI has come to the rescue. Through its Decision Intelligence and AI Express platforms, Mastercard has used predictive analytics powered by machine learning to cut the rate that this happens by 50%. Ajay Bhalla, the company's president for global enterprise, risk, and security, about how this technology works and how AI is now helping Mastercard achieve more of its strategic objectives.

Real-time analytics equals more accurate results:
Bhalla tells me that the quantum leap in the ability to both detect fraud and reduce false declines has come about through its acquisition of California-based artificial intelligence specialists Brighterion. Technology developed with Brighterion has enabled it to move to analyze data in real time. Machine learning algorithms must be incredibly efficient to handle the 75 billion transactions per year happening at 45 million global locations, which are processed by the Mastercard network.

Today, the decisions of whether or not to decline a transaction are based on a constantly flowing stream of data, and self-teaching algorithms, rather than a static sample dataset and fixed rules, which has had impressive results. Bhalla tells me that the artificial intelligence systems, because they are self-learning, are always current and there is no longer a learning lag happening.

He states: What it does is goes through billions of transactions and figures out what is the propensity of the transaction being fraudulent, and it gives this advice to the bank in the system when the transaction goes through for authorization.

It's helped us to catch billions of dollars' worth of fraud. The system uses a real-time stream of transactional data, along with external data including anonymized and aggregated customer information, and geographical information. Geographical information is highly useful because not only does it give an overview of the types of transactions which are normal for a particular area, it also reveals what patterns of fraudulent activity are associated with it. Again, all of this information is aggregated in real time as it happens.

This means that patterns of fraud which are often carried out at large scale by organized gangs, who will target businesses in a particular location, or attempt to cash out at ATMs spread across a city can be detected, tracked and stopped. This is really good from a consumer standpoint because it means faster approval for the consumer, and it means more genuine transactions get approved. And merchants love it because, for merchants, more approvals mean more business, says Bhalla.

The challenges of AI
Building smart, automated systems have been a core strategy at Mastercard for many years, Bhalla tells me, but the acquisition of Brighterion and the incorporation of its technology into Mastercard systems has been a move towards pure AI. Many areas of its business, from customer service to anti-money-laundering measures, are set to benefit from an AI overhaul.

One key challenge has been ensuring a consistently high quality of data as errors in transaction records or other data stores will inevitably lead to even the smartest machines making bad decisions. Bhalla puts his company's success with this down to the more than 50 years' experience it has at generating and verifying transactional records. We have been doing it for many, many years, he tells me, but that's generally the challenge you have to make sure your data is very, very good.

A second challenge is determining the priorities when it comes to making decisions on where in the business to deploy potentially costly AI infrastructure. A decision was made early on that increasing customer satisfaction levels were most likely to bring about the biggest long-term benefits. It's a question of prioritization which are the five key things we need to solve? Bhalla tells me. And you know, our biggest thing we wanted to solve is customer experience, making sure that when you're doing a transaction at the point-of-sale, you're able to do it seamlessly that's our first priority.

Beating the money launderers
To tackle money laundering, many of the AI principles involved are similar to those used in reducing false declines. AI algorithms examine patterns in the transaction data, enabling them to see when groups of people or businesses are acting in a coordinated way, to set up accounts and push through transactions which may involve dirty money.

Another technology natural language processing (NLP) is also deployed here, however. NLP uses algorithms designed to interpret natural human language essentially allowing computers to understand what humans are saying. This means they can draw insights from speech and writing, rather than just the numbers and code they traditionally process. NLP can detect and determine connections between names, and groups of people, and is useful in scenarios where groups of people often use false names and go by aliases, or just subtly alter the spelling of their name, to avoid detection.

Source: HOB