\n
\n
![\"Bunq](\"https:\/\/image.blockchain.news:443\/features\/D8E08E86F8EDBDDCD68414CF49BDD8B1401B11A69515DFF98E6B2B03EE9CF9D7.jpg\")
\n
\n <\/a>
\n <\/figure>\n
European neobank Bunq is leveraging generative AI to tackle financial fraud, significantly enhancing the efficiency of its fraud-detection systems. Utilizing NVIDIA\u2019s accelerated computing technology, Bunq has improved its model training speed nearly 100 times, according to the NVIDIA Blog<\/a>.<\/p>\n Bunq, which boasts over 12 million customers and holds deposits totaling 8 billion euros, has implemented a highly efficient AI-powered transaction-monitoring system. This system, supported by NVIDIA GPUs, accelerates data processing pipelines by over five times compared to traditional methods.<\/p>\n Ali el Hassouni, head of data and AI at Bunq, emphasized the importance of AI in combating financial fraud, a persistent issue in the digital banking sector. Unlike traditional rule-based systems that rely on manually set criteria and result in high false-positive rates, Bunq\u2019s AI system employs supervised and unsupervised learning. This approach not only automates the process but also makes it easily scalable.<\/p>\n By utilizing the open-source NVIDIA RAPIDS suite of GPU-accelerated data science libraries, Bunq has achieved a dramatic increase in the speed of training its fraud-detection models. \u201cWe chose NVIDIA\u2019s advanced, GPU-optimized software, as it enables us to use larger datasets and speed the training of new models \u2014 sometimes by an order of magnitude \u2014 resulting in improved model accuracy and reduced false positives,\u201d said el Hassouni.<\/p>\n Bunq is extending AI capabilities across its operations. The bank\u2019s proprietary large language model and generative AI power Finn, a personal AI assistant available to Bunq customers. Finn can answer user questions regarding their spending and transaction history, enhancing customer service.<\/p>\n Moreover, Bunq is exploring NVIDIA NeMo Retriever to further improve Finn\u2019s accuracy. NeMo Retriever, part of NVIDIA NIM inference microservices, provides models as optimized containers, available with NVIDIA AI Enterprise. \u201cOur initial testing of NeMo Retriever embedding NIM has been extremely positive, and our collaboration with NVIDIA on LLMs is poised to help us to take Finn to the next level and enhance customer experience,\u201d el Hassouni added.<\/p>\n Beyond fraud detection and customer service, AI also supports Bunq\u2019s marketing efforts by analyzing consumer engagement metrics to inform future campaigns.<\/p>\n Bunq’s commitment to utilizing AI technology underscores its mission to create a borderless banking experience, always prioritizing the user. As the digital banking landscape evolves, Bunq\u2019s integration of advanced AI technologies positions it at the forefront of innovation within the financial services sector.<\/p>\nFaster Fraud Detection<\/h2>\n
AI Across the Bank<\/h2>\n