{"slug":"digital-bank-debunks-financial-fraud-with-generative-ai","url":"https://findausecase.com/use-cases/digital-bank-debunks-financial-fraud-with-generative-ai","title":"Digital Bank Debunks Financial Fraud With Generative AI","description":"European neobank bunq, with more than 12 million customers and 8 billion euros of deposits, built an automated, AI-powered transaction-monitoring system to detect fraud and money laundering, replacing labor-intensive rules-based systems with supervised and unsupervised learning. Using NVIDIA GPUs, bunq accelerated its data processing pipeline more than 5x and, using the open-source NVIDIA RAPIDS suite of GPU-accelerated data science libraries, trained its fraud-detection model nearly 100x faster, improving model accuracy and reducing false positives. Bunq is also exploring NVIDIA NeMo Retriever, part of NVIDIA NIM inference microservices, to improve the accuracy of Finn, its personal AI assistant powered by a proprietary large language model.","company":"bunq","industry":"Financial Services","aiCapabilities":["Predictive Analytics","Generative AI","Conversational AI"],"technology":["NVIDIA GPUs","NVIDIA RAPIDS","NVIDIA AI Enterprise","NVIDIA NeMo Retriever","NVIDIA NIM"],"deployment":"Unknown","problemStatement":"Traditional transaction-monitoring systems are rules based, meaning algorithms flag suspicious transactions according to a set of criteria that determine if an activity presents risk of fraud or money laundering. These criteria must be manually set, resulting in high false-positive rates and making such systems labor intensive and difficult to scale.","solutionApproach":"bunq built an automated, AI-powered transaction-monitoring system using supervised and unsupervised learning, powered by NVIDIA accelerated computing. Using NVIDIA GPUs, bunq accelerated its data processing pipeline more than 5x, and using the open-source NVIDIA RAPIDS suite of GPU-accelerated data science libraries (part of the NVIDIA AI Enterprise software platform), bunq trained its fraud-detection model nearly 100x faster compared with previous methods, resulting in improved model accuracy and reduced false positives. Bunq is also exploring NVIDIA NeMo Retriever, part of NVIDIA NIM inference microservices, to further improve the accuracy of Finn, its personal AI assistant powered by the company's proprietary large language model and generative AI.","businessValue":"Using NVIDIA GPUs, bunq accelerated its data processing pipeline more than 5x, and using the open-source NVIDIA RAPIDS suite, trained its fraud-detection model nearly 100x faster than previous methods, resulting in improved model accuracy and reduced false positives. More than half of bunq's user tickets are handled automatically, and AI is also used to spot fake IDs during onboarding and to automate marketing efforts.","evidence":{"band":"high"},"sourceUrl":"https://blogs.nvidia.com/blog/bunq-financial-services-generative-ai","dates":{"publishedAt":"2026-08-22T09:04:08.257Z","publishedAtSource":"pipeline","updatedAt":"2026-08-22T09:04:08.257Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/digital-bank-debunks-financial-fraud-with-generative-ai. Bulk republication requires permission."}