Category Archives: Fraud & Security

When the exact nature of the law is still being decided and the consequences of PSD2 are still unclear, where should you start?

My recent work at FICO to make AI better has drawn upon my background in theoretical physics to create what we call defensive AI. This is needed, because AI-based attacks are not science fiction — they are happening today.

PSD2 means an unprecedented degree of change, and to cope successfully you need tools that can adapt - a strength of machine learning.

I predicted last year that in 2017 financial crime compliance would break through the “cloud ceiling,” and we are certainly seeing more and more organizations deploying AML and KYC technology in the cloud. This is why it’s important that the FICO® TONBELLER® Siron® Anti-Financial Crime Solutions has just achieved Amazon Web Services (AWS) Financial Services Competency status.

Explainable AI has become a hot topic in light of the European Union’s GDPR and society’s increasing reliance on AI systems. How does one of FICO's original Explainable AI innovations stack up?

As I discussed in a previous blog, consumers have not been extensively educated on the impact that PSD2 will have on them. Many of the outcomes of PSD2 will be positive – the Account Information Service Providers (AISPs) and Payment Initiation Service Providers (PISPs) will give people access to a range of new services that will help them to manage their money better and give them more flexibility in the payment providers they use. However, the fraud prevention measures that form an integral part of PSD2 will have a knock-on effect for consumers. In some instances, security checks will make initiating a payment more difficult and irritating. Sometimes the checks may even stop it. Poor Customer Management will Impact the Bottom Line We already know that introducing friction into customer transactions is viewed negatively. Many organisations consider losses to abandoned transactions as important or more important as losses to fraud. PSD2... [Read More]

AI, and more specifically machine learning, are generating enormous buzz in many areas. But are these claims realistic?

If AI is good enough to power self-driving cars, isn’t it good enough to make credit risk decisions? What are the challenges lenders face using AI and machine learning models today? In this podcast for Lend Academy, FICO Blog author Dr. Scott Zoldi talks about his role as FICO’s Chief Analytics Officer, the company’s AI innovations and how they are being applied in credit risk, fraud management and more. Listen to the podcast: “I’m excited that machine learning and AI is the rage again, I think that’s a really positive thing because it’s a tremendously interesting set of technology,” Scott says in the podcast. “What I worry about is it takes a lot of care to properly productionize and operationalize AI. From making sure that models aren’t overtrained, to making sure that you have the proper amount and degrees of freedom, that you really thought about the data you bring into the... [Read More]

Worried about increasing levels of fraud, particularly in remote payments, the regulators have made fraud prevention a cornerstone of PSD2. The regulated use of Strong Customer Authentication (SCA) by payment service providers (PSPs) to secure payments is laid out in the Regulatory Technical Standards for PSD2. However, the use of SCA to secure every payment over €30 could cause problems for PSPs. It could impact the level of customer service they can offer by forcing them to add friction to the consumers’ payment process, forcing consumers to re-authenticate themselves using multiple factors at the point of payment. There is a difficult balancing act between fraud reduction and customer experience. PSPs will be allowed to manage this balance by securing payments using transaction risk analysis (TRA) – as long as they can keep their fraud rates low enough (see the transaction value table from the regulatory technical standard, below). TRA is... [Read More]

While data breaches and ransomware grab the headlines, we’re still seeing fraud growth due to ATM compromises in the US. The fraud growth rate has slowed down from the gangbusters surge we saw in 2015, but consumers and issuers still need to pay attention. The latest data from the FICO® Card Alert Service, which monitors hundreds of thousands of ATMs and other readers in the US, shows a 39 percent increase in the number of cards compromised at US ATMs and merchants in the first six months of 2017, compared to the same period in 2016. The number of POS device and ATM compromises rose 21 percent in the same period. Beyond the numbers, at FICO we have seen the rate of fraud pattern changes accelerating over the last two years. As criminals try to beat the system, we are continually adapting the predictive analytics we use to detect compromises.... [Read More]