Sun Finance, a Latvian fintech company, has successfully automated its identity document extraction and fraud detection processes using generative AI on Amazon Web Services (AWS). The new system, developed in partnership with the AWS Generative AI Innovation Center, significantly improved extraction accuracy from 79.7% to 90.8%. This enhancement led to a 91% reduction in per-document costs and decreased processing time from up to 20 hours to under 5 seconds, addressing previous limitations with traditional OCR and manual reviews. AI
IMPACT Automates identity verification and fraud detection, reducing costs and processing times for fintech operations.
RANK_REASON This is a case study of a company implementing AI tools to improve existing business processes, rather than a new model release or fundamental research.
Read on AWS Machine Learning Blog →
- Amazon Bedrock
- Amazon Rekognition
- Amazon Textract
- AWS
- Generative AI Innovation Center
- Latvia
- OCR
- Sun Finance
AI-generated summary · Google Gemini · from 4 sources. How we write summaries →