How to Streamline Data Science and Feature Creation Workflows in Snowflake

Now available on-demand!

Learn about driving data science workloads to Snowflake using the AtScale semantic layer to eliminate data engineering, accelerate time to prediction, and streamline the management of ML feature stores (“feature engineering”).

Our featured speakers will walk you through an end-to-end demo based on a Credit Card Fraud detection use case to illustrate using Snowflake and AtScale to simplify and accelerate feature creation workflows and embed machine learning models.

In this webinar

You will learn about using:

• AtScale’s semantic layer to enable data, features and relationships to be modeled over Snowflake tables and how to expose business impact of predictions
• Snowpark to enable Data Engineers and Scientists to build data engineering pipelines and execute models for more automated time series feature creation
• Materialized Views to create repository of ML features used for training (scikit-learn) and prediction with feature write-back from AtScale to Snowflake

Who should watch

Data science and AI leaders and practitioners (e.g., Chief Data Officers, data scientists, and analytics professionals) who want to better understand how Snowflake’s Data Cloud and AtScale’s Semantic Layer can improve data science workflows.