Skip to content
Branschnyheter· Analysis

Sun Finance drastically improves ID verification with AI on AWS

Sun Finance has implemented an AI-driven solution on AWS to automate ID verification and fraud detection. This has led to improved accuracy and significantly shorter processing times.

Av Aheadline-redaktionen·8 juli 2026·2 min läsning·Källa: AWS Machine Learning BlogVerifierad signalAI-genererad
Sun Finance drastically improves ID verification with AI on AWS
Sun Finance drastically improves ID verification with AI on AWS
Sun Finance drastically improves ID verification with AI on AWS
By · Policy- & EU-reporter
Last updated

Vad har hänt

Sun Finance, a global fintech operation, has developed an AI-driven pipeline for identity verification (IDV) and fraud detection. The solution is built on AWS services such as Amazon Bedrock, Amazon Textract, and Amazon Rekognition. By combining specialised OCR with large language models (LLM), they have significantly streamlined the process.

Key facts

Noggrannhet före AI-lösning79.7%
Noggrannhet efter AI-lösning90.8%
Kostnadsminskning per dokument91%
Tidsminskning för handläggning20 timmar till under 5 sekunder
Använda AWS-tjänsterAmazon Bedrock, Amazon Textract, Amazon Rekognition

In this post, we show how Sun Finance used Amazon Bedrock, Amazon Textract, and Amazon Rekognition to build an AI-powered identity verification (IDV) pipeline.

AWS, Blogginläggsförfattare · AWS Machine Learning Blog

The 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.

AWS, Blogginläggsförfattare · AWS Machine Learning Blog

You'll learn how combining specialized OCR with large language model (LLM) structuring outperformed using either tool alone.

AWS, Blogginläggsförfattare · AWS Machine Learning Blog

Varför det spelar roll

The new AI solution has improved extraction accuracy from 79.7% to 90.8%. Furthermore, costs per document have decreased by 91%, and processing time has been reduced from up to 20 hours to under 5 seconds. This demonstrates the potential to automate and improve financial processes with generative AI, as the combined effect of the tools exceeds that of individual solutions.

Vem påverkas

Fintech companies handling large volumes of customer identification and fraud prevention are affected. Developers and AI architects working with cloud-based AI solutions, machine learning, and generative AI can benefit from this architecture. End-users seeking fast and secure identity verification are also impacted.

EU-status

Ej relevant för EU-status.

Mer att veta

The architecture also includes a serverless system for fraud detection via vector search. The solution emphasises the synergy between different AI technologies to achieve results that are not possible with individual tools.

Frequently asked questions

Quick answers about this story

Vad har hänt?
Sun Finance har implementerat en AI-driven lösning på AWS för att automatisera identitetsverifiering och bedrägeriupptäckt, med hjälp av Amazon Bedrock, Textract och Rekognition.
När hände det?
Den specifika lanseringsdatumet anges inte i källmaterialet, men artikeln publicerades 23 maj 2024 och beskriver en nyligen implementerad lösning.
Varför spelar det roll?
Lösningen har förbättrat extraktionsnoggrannheten från 79,7% till 90,8%, minskat kostnader per dokument med 91%, och reducerat handläggningstiden från upp till 20 timmar till under 5 sekunder. Det visar på generativ AI:s potential inom fintech.
Vilka verktyg användes i lösningen?
Sun Finance använde Amazon Bedrock, Amazon Textract och Amazon Rekognition för att bygga sin AI-drivna pipeline.
Originalkälla
AWS Machine Learning Blog·aws.amazon.com

Länken öppnar i nytt fönster och leder till utgivarens egen sida.

Verifierad signal

Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.

AI-verktyg i artikeln

Ämnen

#Vision
[ FÖLJ UTVECKLINGEN ]

Få liknande nyheter direkt i mejlen

No affiliate linksCancel anytimeGDPR-friendly
[ Frequency ]
[ What do you want to read about? ]

You'll receive updates on 2 topics.