AWS re:Invent 2021 — A deeper look at SageMaker Canvas
In this video, I demo the newly launched SageMaker Canvas, ““a visual, no-code interface to build accurate machine learning models”. This builds upon a first (skeptical) review.
This time, I start from a CSV dataset for fraud detection on insurance claims. I first load and join the dataset in Canvas. Then, I train models and inspect metrics. Next, I take a look at the underlying AutoML job running in SageMaker AutoPilot. Finally, I share the model in SageMaker Studio.
⭐️⭐️⭐️ Don’t forget to subscribe to be notified of future videos ⭐️⭐️⭐️
- Dataset: https://gitlab.com/juliensimon/amazon-studio-demos/-/tree/master/sagemaker_fridays/season4/s04e10
- SageMaker Friday episode where we used this dataset to train models with AutoGluon: https://youtu.be/7NA5aNrye0s
Top comments (0)