Sun Finance
Get email alerts
New customer deployments for Sun Finance, straight to your inbox. No account needed.
Sun Finance has 2 source-linked AI deployments documented in AIUseCaseHub, across 1 industry and 1 country. Key partners include AWS Generative AI Innovation Center.
2
1
1
Hyperscaler mix
See whether Sun Finance's cases are powered by Microsoft, AWS, GCP, or multiple providers.
How Sun Finance builds AI
Build / Buy / Compose across this company's documented cases
1 of 2 cases classified (50%) · Compare all use-case types
Use case portfolio
Use case types at Sun Finance
Fraud detection leads with 2 of 2 documented cases; 1 distinct type appears across the visible portfolio.
Reported outcomes
1 case reports measurable results
+11.1%
Quality & accuracy
median · 1 metric
−91%
Cost savings
median · 1 metric
−40%
Time & speed
median · 1 metric
Medians of results published in Sun Finance cases, normalized for comparability. See all benchmarks →
Technology snapshot
What Sun Finance uses across visible cases
Computer Vision appears in 2 of 2 indexed cases; 9 named technologies are mentioned, led by Amazon Rekognition.
All Use Cases (2)
Sun Finance automates ID extraction and fraud detection with generative AI on AWS
Sun Finance, a fintech online lending marketplace operating in nine countries, faced challenges with high manual workload for identity document verification and fraud detection due to OCR errors and complex document types across multiple languages. About 60% of loan applications required manual review, resulting in high costs and slow processing times up to 20 hours.They partnered with the AWS Generative AI Innovation Center to build an AI-powered identity verification pipeline and a serverless fraud detection system using Amazon Bedrock (Anthropic Claude Sonnet 4, Amazon Titan Multimodal Embeddings), Amazon Textract, Amazon Rekognition, AWS Step Functions, Amazon API Gateway, AWS Lambda, and Amazon S3 Vectors.The solution architecture uses multi-tier OCR extraction combined with LLM structuring and vector similarity search for fraud pattern detection. Amazon Textract handles primary OCR, Amazon Rekognition is the fallback for low-confidence OCR, and Amazon Bedrock structures extracted text into JSON. Fraud detection combines visual pattern recognition and background similarity analysis using vector search against known fraud patterns.The system increased extraction accuracy from 79.7% to 90.8%, cut per-document costs by 91%, reduced processing time from 20 hours to under 5 seconds, halved manual review workload, and enabled cost-effective scaling to serve lower-value microloan markets.
Sun Finance Uses Amazon Rekognition to Combat Identity Fraud and Remove Customer Friction
Sun Finance, a Latvian fintech company, used to rely on a manual, time-consuming, error-prone identity verification (IDV) process for customer onboarding. The challenge was improving speed, accuracy, and fraud prevention while expanding financial services access globally, including to underserved regions with limited internet and device capabilities.In 2019, Sun Finance automated their IDV workflow by implementing Amazon Rekognition to compare customer selfies with ID documents and detect potential fraud or duplicate accounts. They also adopted Amazon Textract to accurately extract text from documents, including vertically or angled written content.The solution processes identity verification in near real-time, typically completing in 15-20 seconds, significantly reducing manual effort. This automation improved customer onboarding speed and allowed automatic application approvals up to 60% in some markets, enhancing financial inclusion and risk mitigation.
Community
Comments
No published comments yet.
Ask the analyst
A question about Sun Finance the page doesn't answer? I read every one — the good ones get answered here.