Home Retail & Consumer Fraugster a Machine Learning Anti-Fraud Startup Raises $14M

Fraugster a Machine Learning Anti-Fraud Startup Raises $14M

Fraugster, a startup situated in Berlin, applies machine learning and artificial intelligence (AI) algorithms in detecting fraud, particularly in the e-commerce sector.

The company recently fundraised a whopping $14 million in a financing round that was led by CommerzVentures, Commerzbank ’s venture capital subsidiary, and some of Fraugster’s early investors such as Rancilio Cube, Seedcamp, Earlybird, and Speedinvest.

HSB Ventures, global reinsurer Munich Re’s venture capital arm, also took part in the recent succesful funding round.

The company intends to utilize the new capital in expanding geographically in various places around the world such as the United States, Asia, and Europe.

Fraugster claims to have created a useful technology platform for analyzing some 2,500 data points for each transaction in a bid to identify the fraudulent ones.

“In general, the most common fraud behavior we see in the eCommerce space is that of stolen financials, meaning a fraudster steals credit card credentials (usually simply bought online on the dark web) and uses them to buy goods online,” Fraugster’s co-founder and CTO Chen Zamir told Tech.eu. “In order to detect such patterns, our engine is trained to spot minute incoherences in the identity and behavior of the user. […] To spot them, we can look into basic data points like the geographic location of the billing address and the IP address and see if there’s some level of mismatch between them.

“Of course, more sophisticated fraudsters will know how to mask their IP address behind VPNs or proxy IPs and by identifying the IP as such, that would on itself serve as a data point we would use to analyze the transaction.

Another example of more sophisticated methods we can use for fraud detection is to analyse email addresses thoroughly to identify ‘bogus’ emails (i.e. asdasd@gmail.com), match the email to the name of the user and even find fuzzy bad networks (i.e. a fraudster that is using repeatedly emails such as test1@gmail.com, test2@gmail.com, etc. where the email is similar but not a straight match that a machine would easily identify).”

Established back in 2014, Fraugster is involved in monitoring millions of daily transactions. Some of its clients include payment service providers such as Six Payments and Ingenico ePayments.

READ MORE: 10 Powerful Applications of Artificial Intelligence in Retail

The startup was started with the vision of designing and building an anti-fraud technology, with the ability to come up with a fraud-free world where no one has to worry about ever managing risk again.

Fraugster’s work in the payments industry gave the company a first-hand taste of fraud, particularly for e-commerce merchants.

When operating in this industry, the company discovered that all the existing anti-fraud solutions were built using obsolete technologies, which meant that they were not sufficient for dealing with complex cyber criminals.

Fraugster’s team of payment and AI specialist has spent the last couple of years designing a proprietary advanced technology.

The result of this hard work led to the creation of a sophisticated artificial intelligence (AI) technology.

The company claims that this AI technology has the potential to maximize revenue and get rid of payment fraud.

Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...