Energy Price Forecasting using Snowflake Native App and Snowpark ML
Naveen Alan
Overview
This solution architecture shows how to forecast wholesale energy prices with YesEnergy data from Snowflake Marketplace using Snowpark ML.
- Get YesEnergy data from Snowflake Marketplace
- Use Snowpark for pre-processing, feature selection, and model training
- Build a Native application that deploys the XGBoost model for price prediction
- Build a Streamlit App for the User Interface
Solution Architecture: Forecasting Wholesale Energy Prices using Snowpark ML
- In this use-case, we develop accurate price forecasting models and develop new forecasts from these models (i.e. run inference) on an hourly schedule
- First, Snowflake environment is set up with access to YesEnergy data from Snowflake Marketplace
- Then we select the date range to be used for Training and Backtesting
- Perform price and spike forecasting and view the performance results
- Deploy the selected model, schedule the inference intervals and training
Get Started
Updated 2026-04-29
This content is provided as is, and is not maintained on an ongoing basis. It may be out of date with current Snowflake instances
