AI use case

Sun Finance: GenAI-Powered ID Verification and Fraud Detection

Sun Finance (Latvian fintech, 4M evaluations/month) deployed GenAI on AWS for ID extraction and fraud detection — improving extraction accuracy from 79.7% to 90.8% and cutting p…

Browse catalog

At a glance

Core facts from this catalog record. Primary narrative lives in the hero above; full raw fields follow in the next section.

Company/Organization: Sun Finance Group
Industry: Financial Services
Location: Riga

Record fields

Every column from the source row, in stable order. URLs open in a new tab.

Title

Sun Finance: GenAI-Powered ID Verification and Fraud Detection

Content

Sun Finance processes a new loan request every 0.63 seconds across 9 countries. Partnered with AWS Generative AI Innovation Center to build an IDV pipeline using Amazon Bedrock (Claude Sonnet 4), Textract, and Rekognition. Solution improved extraction accuracy from 79.7% to 90.8%, cut per-document costs by 91%, and reduced processing time from up to 20 hours to under 5 seconds. The fraud detection system uses vector similarity search (Amazon S3 Vectors) and Claude-powered visual pattern detection. Project went live January 22, 2026 after 35 business days of production deployment.

URL

https://aws.amazon.com/blogs/machine-learning/sun-finance-automates-id-extraction-and-fraud-detection-with-generative-ai-on-aws/

Continue exploring AI deployments in the catalog.

Back to use cases