{"slug":"innovating-banking-efficiency-national-bank-of-greece-transforms-operations-with-microsoft-azure-ai-document-intelligence","url":"https://findausecase.com/use-cases/innovating-banking-efficiency-national-bank-of-greece-transforms-operations-with-microsoft-azure-ai-document-intelligence","title":"Innovating banking efficiency: National Bank of Greece transforms operations with Microsoft Azure AI Document Intelligence","description":"National Bank of Greece (NBG), which serves 6 million customers across 356 branches, built a Document AI solution on Azure AI Document Intelligence (formerly Form Recognizer) to replace a limited rule-based OCR process. Built in under four months after analyzing 50 million pages to create a training dataset, the solution now supports about 20 document categories across nearly 60 document templates (tax forms, payroll certificates, IDs, energy certificates, utility bills), processes documents at under 0.5 seconds per page, and integrates with six customer-facing digital banking applications. Accuracy improved to approximately 90%, the system is tuned to recognize the Greek language, and NBG now processes over 700,000 pages per month.","company":"National Bank of Greece","industry":"Financial Services","country":"Greece","aiCapabilities":["Document Intelligence"],"technology":["Azure AI Document Intelligence","Azure Cognitive Services","Azure Machine Learning"],"deployment":"Public Cloud","problemStatement":"NBG's previous rule-based OCR solution was limited to a single document type (PDF), a considerable bottleneck given the bank handles more than 50 document types. The process was cumbersome, prone to errors, and costly: a customer would bring or email documents to a branch, where an employee would print, scan, and send them to the back office to manually extract the information.","solutionApproach":"NBG built a Document AI solution using Azure AI Document Intelligence (formerly Form Recognizer), completed in under four months after analyzing 50 million pages of documents to create a training dataset. Azure Cognitive Services was used to tune the solution to recognize the Greek language. The solution integrates with six customer-facing digital banking applications and now supports about 20 document categories across nearly 60 document templates, including tax forms, payroll certificates, IDs, energy certificates and utility bills.","businessValue":"Documents are processed at a rate of below 0.5 seconds per page, and accuracy has increased to approximately 90%, cutting down on time spent on manual verification. The bank now processes over 700,000 pages per month, and with 10-20 sample documents the team can release a new model to support a new use case within two days.","evidence":{"band":"high"},"sourceUrl":"https://www.microsoft.com/en/customers/story/1774373123930343901-nbg-azure-banking-and-capital-markets-en-greece","dates":{"publishedAt":"2026-08-17T01:22:12.467Z","publishedAtSource":"ledger","updatedAt":"2026-08-18T10:29:44.442Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/innovating-banking-efficiency-national-bank-of-greece-transforms-operations-with-microsoft-azure-ai-document-intelligence. Bulk republication requires permission."}