BBVA collaborates with MIT to enhance card fraud detection

Maria Nikolova

The aim is to reduce the level of false positives when detecting fraudulent card transactions.

BBVA has partnered with researchers from the Massachusetts Institute of Technology (MIT) in an effort to improve the efficiency of card fraud detection. In particular, the aim is to minimize the level of false positives in fraudulent card transactions.

For years, banks have been using machine learning techniques to detect card fraud. Algorithms are trained to learn to recognize behavioral patterns typical of fraudulent transactions and block subsequent ‘suspicious’ operations. However, this results in false positives. When customers pay an unusual amount of money or use their cards far from their usual locations, their cards often get blocked because the system erroneously qualifies these anomalies as “suspicious”. Let’s recall that, in March last year, for instance, there was a flood of complaints in Russia about bank accounts being blocked following checks for AML compliance conducted by automated systems.

The reason for this is that the automated systems using machine learning are subject to a series of limitations when applied to card fraud. As their ability to detect actual fraudulent transactions grows, so does the number of false positives they derive; put otherwise, the number of legitimate transactions they erroneously label as fraudulent also rises.

Aiming to improve the situation, BBVA’s Corporate Security and Engineering Risk (CS&ER) team started collaborating with MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) in 2015. The MIT and BBVA research team used the Deep Feature Synthesis method, a model developed by two MIT researchers, Kalyan Veeramachaneni and James Max Kanter, which makes it possible to derive highly detailed features from datasets in an automated manner.

This new approach allowed the research team to derive over 200 new additional features from every transaction. These features can be used to describe the behavior of card transactions in greater detail and improve the results yielded by the detection engines. Some of these new features used to fine tune true positive results indicate, for example, whether the user was physically present while the transaction was taking place, or the average time spent in certain stores. This helps to more accurately identify when a particular card user’s transaction veers from the norm.

So far, tests are yielding promising results. False positives have fallen markedly, while keeping the same level of fraud detection, compared to other existing products and systems. Specifically, applying the model to a dataset of 1.8 million BBVA transactions cut the number of false positives by 54% over traditional models, saving the bank approximately €190,000.

Applying the results of this research to BBVA’s fraud detection systems has proven that they have the potential to improve customer satisfaction in card transactions without compromising current security standards.

Read this next

Digital Assets

US court greenlights IRS to track down crypto investors

A federal court has authorized the US Internal Revenue Service (IRS) to issue a so-called John Doe summons for taxpayers who may have failed to report and pay taxes on cryptocurrency transactions. 

Executive Moves

GCEX hires American Express’ veteran Marilu Revelli as marketing director

GCEX, a digital asset and FX technology platform for institutional and professional clients, has appointed Marilu Revelli to the role of Marketing Director.

Crypto Insider lists DeFiChain’s DFI token amid growing popularity

Bitcoin-based DeFi platform DeFiChain announced the listing of its native DFI token on, one of the world’s leading cryptocurrency exchanges.

Digital Assets

Binance in discussions with Japan regulators to relaunch operations

Binance, the world’s largest crypto exchange by traded volume, is reportedly seeking a license to operate in Japan after its exit from the country four years ago.

Digital Assets

OKX Chain integrates .crypto domains to simplify wallet transactions

Unstoppable Domains, a company building Blockchain domain names, has entered a partnership with EVM and IBC compatible chain OKC (OKX Chain). This collaboration will grant OKC’s users the ability to simplify deposits and withdrawals within the regulated fiat-focused crypto-asset exchange.

Retail FX, Technology

MetaTrader’s iOS issue opens brokers’ eyes to other trading platforms

In a surprising (or-not-so-surprising) move, Apple has removed MetaTrader 4 and MetaTrader 5 from its App Store in a huge blow for the leading FX trading platform provider.

Retail FX

Pepperstone adds analytics and automated trading tools free of charge

“We look forward to bringing significant value to Pepperstone traders and making a real, positive impact in their daily trading habits. We are excited to welcome them on board.”

Retail FX

FP Markets wins Best Global Value Broker for 4th consecutive year at the 2022 Global Forex Awards

“We greatly appreciate the continued international recognition as at FP Markets we pride ourselves on these attributes and these prestigious awards are testament to the hard work from our global team to always provide our clients with the ultimate trading experience.”

Inside View

How to Engage Your Customer at Every Stage of Their Journey

As many as 89% of successful businesses say that providing assistive customer experiences is critical to their growth. That’s because a mere 5% increase in customer retention can boost profits by 25% to 95%.