Hamburg, April 29, 2020
Hamburg, April 29, 2020
97 percent affected: fraud and fraud attempts are everyday business for many online providers and retailers in Germany
Exposes bot networks and fraudsters: AI-supported plug-in solution performs identity and fraud checks, gives warnings in real time, and thus protects against abuse
Less manual, individual processing: machine learning reduces the number of cases requiring clarification by over 80 percent compared to conventional, rule-based systems
These are good times for online fraudsters: almost every German now shops online.
According to studies by the digital association Bitkom, already 94 percent of them do, i.e., 55 million customers. One in three orders something online at least once a week. This poses risks, because credit card fraud, identity theft and account takeover are the rule rather than the exception on the web.
In Germany and Switzerland, 97 percent of online shops have previously been a victim of fraud. This is shown by the CRIF BÜRGEL "Fraud in E-Commerce" survey from spring 2020, held among 110 online and mail order companies from Germany and Switzerland. According to another study by LexisNexis, there were 277 million online attacks worldwide in the first six months of 2019 alone, an increase of 13 percent. However, these are only the human-initiated attacks: during the same period, so-called bot attacks against online retailers increased by 305 percent. Fraudsters use accounts created by bots in order to, for example, test online identities or credit card data and redeem virtual vouchers. Their approach is becoming ever more advanced and more difficult to detect.
"Four fraud patterns are causing problems for online providers," says Kai Wanka, Head of Fraud Solutions at the information service provider CRIF BÜRGEL. Fraudsters most commonly use falsified name or address data. 71 percent of shops are acquainted with this. Then comes identity theft: 68 percent of retailers have already experienced a customer claiming to be a completely different, real, person. 42 percent were affected by friendly fraud, fraudulent representation to obtain a contract. This is what you call an order where the buyer already knows in advance that they cannot or will not pay the invoice, but still receives the goods. At 52 percent, more than half of fraud cases are the result of stolen payment data, such as from credit cards. Millions of dollars of damage are caused by this every year. "Fraud prevention is therefore becoming increasingly important, because data theft not only concerns online shops, but also providers of digital services, such as banks, telecommunications and mobility providers, and hosting and web services, streaming services, gaming and comparable providers – anywhere where fraudsters can abuse information for economic gain," says Wanka.
Protection for providers and their customers is provided by HYBRIGHT, CRIF BÜRGEL's new software solution for risk assessment and fraud prevention. Supported by machine learning, checks of customer behaviour as well as identity, location and device data detect abnormalities while an application or order process is still ongoing and triggers an alarm.
"The digital footprint of each customer grows with every interaction on the web. And our tool tracks it like a motion detector." Behavioural biometrics, predictive analytics and automated pattern recognition make it easier to differentiate between good and less good customers and to screen out fraudsters before they get a chance. "For a top customer experience and good prevention, providers need to know: Who is my customer, what do they want and how do they behave – typically?" explains Wanka.
"But no online provider can know all of its customers as well as the traditional corner shop did back in the day. Even if it has very, very well-maintained customer relationships – how is it supposed to suspect that a fraudster has taken over the account of a good customer? And if you have, let's say, 100,000 users in your online shop, you can't always have all the information to hand to effectively prevent fraud," continues Kai Wanka.
Read more: www.crifbuergel.de/en
