Loading
4 Essentials to Detect and Prevent Scams Using Advanced Analytics
Scams are growing globally as fraudsters innovate and evolve. Advanced technology can help level the playing field and prevent future attacks.
Fighting scams in 2021 is a race: Criminals are rapidly bringing more and more sophistication and innovation into their attack methods, and banks are racing to match or outpace the attackers with new tools, technology, and techniques.
The volume of attacks by fraudsters is growing across the globe:
In the U.S., complaints about fraud incidents rose 69% in 2019 to nearly 800,000, according to the Federal Bureau of Investigation’s (FBI’s) latest annual Internet Crime Complaint Center Report, with losses of $4.2 billion.
In Australia, scams are up 89% through the first nine months of 2021 versus 2020, with the highest growth occurring in phone-based scams
In Singapore, scam losses grew by 165% in the first six months of 2021, police reported.
In the UK, scams are up 30%, with even higher growth in Covid-19-related scams.
New opportunities for scammers
The Covid-19 pandemic has created a new range of opportunities for criminals to exploit – and they’ve taken full advantage. In the UK, scammers have been contacting consumers offering Covid-19 vaccination appointments and saying that bank account information must be provided to confirm the appointment. The victims who share their bank details then find their accounts depleted. Other growing and popular fraud methods involve email communications. Some promise consumers they have unclaimed tax refund money, others claim a valuable package can’t be delivered without additional information, or that action is needed on their Netflix or telecom account to maintain service.
Scammers are expanding their use of all types of media, with particular growth in phone-based scams. “Smishing” – the use of text messages instead of email – is also growing rapidly, as is “pharming,” in which texts, emails, or social media posts direct consumers via links to malicious websites that download malware onto their smart phones and PCs.
Once criminals have managed to scam money out of someone’s account, they will often use a network of other bank accounts to exfiltrate their illicit proceeds and attempt to hide their tracks. These are known as mule accounts, and they are in increasing demand from criminal organizations.
Bank fraud and scam prevention
The landscape of responsibility for covering fraud losses is changing. Increasingly, there is an expectation that banks should protect consumers and reimburse them when they have been a victim of a scam. In the UK, for example, since the Contingent Reimbursement model voluntary code was introduced in 2019 to define when and how victims should be reimbursed by banks, the reimbursement rate for fraud losses has risen from 20% to an estimated 45%. UK banks have also stepped up their efforts to warn consumers about scams via their apps and online banking sites, which is raising the level of consumer awareness and alertness.
Scam detection using advanced analytics
But even as bank customers grow more savvy about scams, more financial transactions of all types move online to computers, smart phones, and other mobile devices, and the opportunities for fraud attacks proliferate. Financial institutions face a huge dilemma: How can they stop it?
Defense in depth, or “layered defense,” has long been a best-practice strategy for business organizations defending against cyber attackers trying to penetrate their networks. The same concept holds true for bank fraud prevention measures: Layering additional methods of scam detection and prevention improves results.
The most successful scam detection and prevention results are being achieved by banks that:
Use advanced analytics technology to identify fraud tactics and spot subtle patterns. Artificial Intelligence (AI) and machine learning are able to identify potential fraud patterns that a human investigator would need much longer to spot.
Analyze more data. This is a major advantage in using AI, and being able to bring a diverse range of internal and external data types together on one platform for analysis is key.
Consider high-risk accounts as a network and calibrate the analysis. Although indicators viewed in isolation may identify scams, there is a risk of false positives, and it’s often too late to prevent the fraud occurring.
Target their education programs at customers identified by a bank as high-risk, either due to their customer or transaction profile or because they fell victim to fraud in the past.
To win the race against fraudsters, it pays to be agile, innovative, and proactive. In fact, that is not just an advantage; it’s a necessity to prevent scams.
