Architecture review for Custom Anomaly AI


I am trying to build a architecture for custom anomaly ai on AWS for my startup. Please let me know if my way of thinking is correct or not

  1. Data Ingestion: Ingesting the data into AWS S3 in JSON format
  2. Data Preprocessing: Converting JSON format to Excel format using AWS Glue and storing it back into S3
  3. ML : Using AWS Sagemaker to learn from the Excel format created
  4. Quicksight to show the data for data visualization

is my way of thinking correct here?

  • May I ask why converting json to excel?

  • it is just my way of thinking. I am open ears to learn in case you have any other idea. But I want to implement Custom Anomaly AI detection.

1 Answer

I don't see the point of converting to Excel if you are not going to use a spreadsheet editor to open but instead using Quicksight. Any other format like CSV will allow you better support and parallelism.

profile pictureAWS
answered 11 days ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions