European neobank bunq has implemented generative AI (genAI) from Nvidia to address fraud and money laundering activity.

With over 12 million customers and €8 billion worth of deposits made since its launch in 2012, bunq is one the largest neobanks in the European Union.

bunq's new automated transaction-monitoring system is different to traditional models, which are often rules based. These systems use algorithms that flag suspicious transactions according to a set of criteria to determine if an activity presents risk of fraud or money laundering. Because these criteria are manually set, they can result higher false positive rates.

The neobank's new AI-driven system uses supervised and unsupervised learning to completely automate the process.

“AI has enormous potential to help humanity in so many ways, and this is a great example of how human intelligence can be coupled with AI,” said Ali el Hassouni, head of data and AI at bunq.

Bunq was able to achieve this by deploying Nvidia GPUs, which sped up its data processing.

The bank has also been able to train its fraud-detection model nearly "100x faster" using an open-source suite of GPU-accelerated data science libraries.

Bunq has said that it aims to roll out AI across its operations.

“We’re constantly looking for new ways to apply AI for the benefit of our users,” el Hassouni said. “More than half of our user tickets are handled automatically.

"We also use AI to spot fake IDs when onboarding new users, automate our marketing efforts and much more.”

The company also has a personal AI assistant for its customers which is based on its proprietary large language model and generative AI.

The assistant is able to answer questions like: “How much did I spend on groceries last month?” or “What’s the name of the Indian restaurant I ate at last week?”

Bunq is currently testing collection of genAI microservices in early access with the aim of improving its AI assistant.

---