kyc_aml · finance · workflow

Sun Finance automates ID extraction and fraud detection with generative AI on AWS

Sun Finance processed 80,000 monthly microloan applications but approximately 60% required manual operator review, primarily due to OCR extraction errors across multiple languages and ID document types. Per-document costs and approximately 3 FTEs dedicated to manual verification blocked expansion into lower-value loan markets, while about 10% of daily requests were fraudulent, requiring time-intensive manual review.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Loan application triggers ID check
A loan application arrives and the ID image is submitted to the extraction pipeline via an AWS Lambda function.
Tools used
Amazon Titan Multimodal EmbeddingsClaude Sonnet 4Amazon API GatewayAmazon CognitoAWS WAFAWS KMSTerraform
Outcome

The multi-tier 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. Manual intervention is projected to drop from 60% to 30% of applications, with staffing projected to decrease from approximately 3 FTEs to approximately 1 FTE.

What failed first

Sun Finance's 2019 IDV system hit accuracy limits as the company expanded into regions with languages underrepresented in OCR training data and multiple ID formats. A replacement attempt using Claude Sonnet 4 alone via Amazon Bedrock achieved only 61.8% accuracy—below the existing baseline—because the model's built-in privacy safeguards refused to extract PII from identity documents, causing ID number extraction to fall to only 43%.

Results
Time savedunder 5 seconds
Volume90.8%
Cost replaced91% reduction
Running sinceJanuary 22, 2026
Source

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

How we source this →

Grounding & classification
Source type: technical build writeup
52 fields verified against source quotes, 7 dropped as unverifiable.
computer visiondata extractiondocument aifraud detectionidpocrform submissionid documentfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedvendor confirmedworkflow describedfinancial servicesaccuracy improvementautomation ratecost reductioncycle time reductionemployee productivitytechnical build writeupback office opscompliance monitoringkyc amldocument to recordextract classify route