Sign up for The Paypers newsletter Follow The Paypers on LinkedIn Follow The Paypers on Twitter Follow The Paypers on Facebook Follow The Paypers on Google +
The Paypers, paypers, Insight in payments, News, Reports, Events
 advertisement
Case study

Feedzai fraud platform creates 74 percent increase in account opening approvals with no new fraud

Thursday 19 April 2018 | 08:00 AM CET

A Top 10 US Retail Bank sought an AI-enabled fraud prevention partner to manage risk for its account opening use case. This bank chose Feedzai.

A shifting business model causes pain

When the bank made the shift from a branch-heavy to a thin-branch model, it began to offer its core checking account via an online sign-up process. However, the bank found itself rejecting 60% of new applications due to the inability to assess risk efficiently.

In addition to its low approval rate, the bank’s account opening workflow had a burdensome layer of friction: call-outs for external data, like bureau information and credit information, were performed for every applicant, irrespective of risk analysis.

This bank sought a fraud-fighting system that could increase application approvals for legitimate customers without increasing operational overhead or adding friction. The bank also sought a system that could provide clear explanations for its decisions, so that manual review teams could provide an audit trail for compliance.

Partnering with Feedzai to fight new fraud

For its fraud prevention platform, the bank partnered with Feedzai. We streamlined the entire risk management workflow for customer accounts, solving for customer experience and fraud at the same time. Our AI-enabled platform ingested application, network, and third party data to create real-time profiles for customers, and applied a combination of machine learning models and configured rules to produce risk assessments at each stage in the account opening process.

Total risk management workflow for customer accounts
[click to enlarge]

In our total risk management workflow for customer accounts, risk assessments above specified thresholds either trigger automated escalations, such as “out of wallet” questions, or manual review processes. Operational dashboards allow fraud and risk teams to monitor the end-to-end performance of the customer's onboarding process. And whitebox explanations add a human-readable semantic layer onto the underlying machine logic.

Powered by artificial intelligence

Fraudsters are opportunistic, attuned to vulnerabilities, and often working in coordination to systematically compromise the security of a particular network. They represent a constant threat, and detecting their new and emergent behavior represents a critical challenge for banks. The legacy approach is to use rules alone to find these fraudsters, but there is a limit to what rules can foresee, because they can only look at the past.

The shortcomings of rules are especially evident in account opening scenarios, where there’s an absence of historical data. How can a bank overcome this so-called “thin file problem” to build intelligence and make confident decisions about fraud?

The power of machine learning is to track and connect emergent fraud signals in real time to stop fraud in its tracks. And a system that can integrate internal and external data from multiple channels can begin to break down data silos and make holistic decisions about the person behind each application.

The results are in

The new streamlined verification flow solved for fraud and customer experience at the same time by increasing application approvals without incurring additional fraud. Manual overhead and false positives drastically decreased. Meanwhile, customer experience improved greatly with a seamless and instant flow. And there was no discernible difference in experience for customers with higher risk profiles, because riskier customers were simply required to answer additional questions.

The results were:

  • 74% increase in application approvals,

  • 0% increase in fraud,

  • 10x reduced false positives.

And as data streams continue to proliferate, this bank can integrate them in risk models within weeks, a process that used to take months. The outcome of partnering with Feedzai has met everyone’s expectations: the Top 10 US Bank moved up while bringing fraud exposure down.

About Feedzai

Feedzai is coding the future of our digital economy with the most advanced risk management platform, powered by big data and artificial intelligence. Some of the world’s largest organisations use Feedzai’s machine learning technology to manage the risk associated with banking and shopping, whether it’s in person, online, or via mobile devices.

 advertisement
 advertisement
 advertisement
 advertisement