Feedzai fraud detection platform uses AI and biometrics


If you are preparing to withdraw money from an ATM in a foreign country, take a good look at where you insert your card. Go ahead, grab it and shake it a bit. The plastic case your card is in is sometimes replaced with a bogus case that captures your PIN and card information while you make a legitimate transaction. When you walk away from the ATM, don’t react to any “Watch out for our pickpockets!” Signs you might see. Hungarian police discovered that the pickpockets themselves were putting up signs. This is because people instinctively search for their valuables when they are alerted to pickpockets, immediately telegraphing where they are looting.

If you think there is a lot of fraud in the real world, wait and see what happens in the digital world. This is probably why Feedzai, another private company that recently joined the unicorn club, is gaining traction for its machine learning platform to prevent and detect fraud and money laundering in the financial services industry. .

Fraud is on the rise

And if you believe the statistics – many of which come from Feedzai, which publishes quarterly financial crime reports – fraud in the financial services industry is out of control. All Internet, telephone and in-person banking fraud (do people still do that?) – grew 159% in the first quarter of this year compared to the last quarter of 2020. Online banking, which accounts for 96% of all banking transactions, accounted for 93% of all fraud cases. The analysis would cover more than 12 billion global banking transactions.

But let’s remove the implied bias and turn to a neutral party: Consumer credit reporting giant TransUnion, comparing a similar period, said alleged attempts at digital fraud on financial services rose 149%. This is what you might call a growing market:

Growth of the fraud detection and prevention market in the billions. Credit: Statista

With a company name that cannot be spelled over the phone, Feedzai appears to be in pole position in the fraud detection and prevention market.

A new IA Fintech unicorn

Founded in 2009, the Silicon Valley-based startup raised $ 277.5 million in the disclosed funding, most of the money came from a massive $ 200 million Series D in March. This pushed the company up to a valuation of $ 1 billion.

While most of the names on the investor list lean towards the venture capital (VC) side of the spectrum, like Sapphire, another notable name is the venture capital arm of Citigroup (C). It’s usually a pretty good sign when one of the biggest banks in the world not only buys your product but also invests in it, including an undisclosed company in 2016. In fact, Feedzai’s war chest could be at north of $ 300 million, as the private firm just raised another undisclosed firm earlier this month from a small venture capital firm based in Madrid, Spain called Conexo Ventures. The investment will make a little more sense later in our story.

How does Feedzai use AI to detect fraud?

The answer: Pretty fast. The startup says its platform can calculate a risk score in three milliseconds, evaluating thousands of decisions to evaluate a transaction in real time. Machine learning models identify transaction patterns by analyzing customer behaviors and profiles, as well as leveraging third-party external data that models use to assess transaction risk and detect patterns of financial crime. Customers can customize the templates by adding other rules and lists to refine the approval, rejection, or review decision. The result would be transparent with clear documentation for the decision.

Feedzai AI platform.
The Feedzai AI platform clearly documents its decisions and provides engaging visualization tools to detect larger fraud patterns. Credit: Feedzai

But it’s not all machine-driven: A risk analyst examines transaction scores and fraud alerts, passing anything suspicious to a company’s senior data analyst. This person uses Feedzai’s AI-powered visual analysis tool called Genome which can help uncover larger patterns of financial crime and fraud. All decisions are fed back into the machine learning model to improve performance over time.

Feedzai use cases

The platform protects financial institutions from fun cases involving account openings, transactions and money laundering. Its customers include retail banks, payment processors and merchants, among others. Feedzai says it monitors businesses that serve more than 800 million customers in 190 countries, with products protecting half of the population in the UK and Canada, as well as four of North America’s top five banks. But here’s the statistic that really caught our attention: Over 20% of global money goes through the Feedzai platform, according to the company.

Feedzai customer benefit statistics.
Credit: Feedzai

Besides Citibank, other large financial institutions such as Fiserv (FISV) and Santander (SAN) are also clients, as well as fintech companies like SoFi (SOFI) and Mox of Standard Chartered. Another client of the new generation of financial institutions is SafetyPay, a digital alternative payment platform focused on Latin America and Europe. SafetyPay allows consumers to make online purchases by wire transfer or cash without sharing their information online. Feedzai comes into the picture by monitoring payment activity patterns and comparing them to a customer’s historical data to authenticate transactions.

Feedzai acquires Revelock

There is no doubt that Feedzai will use some of its new fortune to further develop its platform. In fact, the company wasted no time doing just that by acquiring Revelock, a behavioral biometric platform based in Madrid, for an undisclosed amount last month. Founded in 2015, the startup had raised $ 14.3 million nowadays. Most of the investors are headquartered in Spain, including a name that appeared earlier – Conexo.

Biometrics uses a variety of technologies to verify or authenticate identity, ranging from facial recognition on your iPhone and voice verification to the way you manipulate your mobile device. In Revelock’s case, the company developed a hybrid AI model that powers BionicID, a unique digital identifier created by collecting the thousands of biometric, behavioral, device, and network data points from each user. It constantly analyzes user behavior, from login to logout, to every interaction. If everything looks cool, the session continues uninterrupted. Otherwise, Revelock takes action, which may involve verifying the user with strong authentication, ending the user session or lock the account.

Revelock BionicID platform
Apparently ticks are part of the threat information. Credit: Revelock

Feedzai has big plans around this acquisition to create “the world’s largest financial intelligence network, a vault of over a trillion data points, sessions and profiles of good and bad actors.” The network would combine Feedzai’s 150 billion data points for fraud detection with Revelock’s BionicID, a kind of human digital twin, based on how it’s described. Of course, each session promises complete anonymity to “ensure that people are treated as persons and not as data points”.


The digital shift in the economy is becoming seismic, with the Rona shaking things up even more when people started to treat paper money like the plague, with ATM withdrawals down 58% in 2020. About 41% of Consumers have moved from cash payments to online / phone payments. and more than half of them don’t plan to switch back to cash, according to Zelle, the mobile payment app that shares your every social media transaction by default. Meanwhile, the bad guys haven’t missed a beat, finding new ways to separate people from their money and their identities. Fintech companies like Feedzai are betting they can outsmart them with artificial intelligence.

Technology investment is extremely risky. Minimize your risk with our equity research, investment tools and portfolios, and find out which tech stocks you should avoid. Become a Analyze Premium member and find out today!

Leave A Reply

Your email address will not be published.