Scalable Feature Engineering and Model Training With Scikit Learn and XGBoost in Snowpark ML

Many developers and enterprises looking to use machine learning (ML) get bogged down by the operational complexity of building scalable models. With Snowpark ML, teams can use familiar Python frameworks for preprocessing and feature engineering for models that can be trained, managed and executed entirely in Snowflake without any data movement, silos or governance trade-offs. Decile, a customer data and analytics platform built by and for marketers, uses Snowpark ML to build models that predict lifetime value and purchase patterns.

Watch this webinar with Snowpark ML expert and customer Decile to learn more about how to:

• Improve performance and scalability with distributed execution for common scikit-learn preprocessing functions
• Accelerate model training for scikit-learn, XGBoost and LightGBM models with distributed hyperparameter optimization
• Easily migrate from Spark ML to Snowpark ML