Build a no-code ML workflow with Snowflake, Amazon SageMaker Canvas and Amazon Quick – Part 2: Data preparation and model building with Amazon SageMaker Canvas
aws ·
This article is Part 2 of a blog series on building a no-code ML workflow with Snowflake, Amazon SageMaker Canvas, and Amazon QuickSight. It details data preparation and model building using SageMaker Canvas, a visual no-code service for creating ML models. The guide explains connecting Canvas to Snowflake, using Data Wrangler to run SQL queries that create outlier features and enrich data with temporal, demographic, and merchant attributes. It covers joining datasets, adding custom formula columns, and dropping sensitive columns. A Data Quality and Insights Report is run with IS_FRAUD as the target column to identify data issues. Finally, the prepared data is exported to build a fraud detection model using the XGBoost algorithm, with IS_FRAUD as the target column.
aws