Home/Projects/AWS AI/Project 2
IntermediateAWS AI project · about 10 hours

Document intelligence with AWS AI services

Extract, translate and analyse text from scanned documents with managed AI services.

The real-world brief

An insurer receives thousands of scanned claim forms and wants the key fields extracted automatically.

What you will build

  • An upload-triggered pipeline
  • Fields extracted with Textract
  • Entities and sentiment from Comprehend
  • Results saved as JSON

Skills you will practise

Managed AI servicesServerless pipelinesEntity extractionCost awareness

Tools

Amazon TextractAmazon ComprehendAmazon TranslateAWS LambdaAmazon S3

Project tasks

The detailed steps, checklists and trainer review open in the SOTT student portal for enrolled students.

1Upload trigger Steps in portal
2Extract Steps in portal
3Analyse Steps in portal
4Measure Steps in portal

How companies use AWS AI

Banking: Spotting fraud. Rule-based checks missed new fraud patterns. A machine learning model scores each transaction and flags unusual ones for review. More fraud is caught with fewer false alarms.

Retail: Demand forecasting. Stores ran out of popular items and overstocked others. A forecasting model predicts demand per store and product each week. Stock-outs and waste both went down.

Telecom: Predicting customer churn. Customers left without warning. A churn model ranks customers by risk so the retention team can call them first. More at-risk customers were kept.

Questions

Can I add the Document intelligence with AWS AI services project to my resume?

Yes. Once your trainer approves it, list it under Projects with the tools you used, one line on the problem it solves and a link to your repository and demo video.

How long does this project take?

About 10 hours of hands-on work, and it fits best after week 8 of the AWS AI course.

Where do I get the step-by-step tasks?

Enrolled students get every task with steps, "done when" checks, the submission form and a trainer review in the SOTT student portal.