Icon

03_​Snowflake_​Model_​Deployment

Customer Churn Predictor Deployment with KNIME and Snowflake

This workflow is an example of how to deploy a customer churn predictor as Snowflake User-Defined Function. This way the prediction is pushed down into Snowflake were the data resides. The prediction result is persistet as new database table in Snowflake.

URL: Blog post https://medium.com/snowflake/build-a-churn-predictor-with-knime-and-snowflake-5f32a1fa8f7a
URL: KNIME Snowflake Extension Guide https://docs.knime.com/latest/snowflake_extension_guide/index.html
URL: Snowflake ETL workflow https://kni.me/w/vDONDGR5-kZAtvtw
URL: Kaggle dataset https://www.kaggle.com/becksddf/churn-in-telecoms-dataset

Customer Churn Predictor Deployment with KNIME and SnowflakeThis workflow is an example of how to deploy a customer churn predictor as Snowflake User-Defined Function. This way the prediction is pushed down into Snowflake were the data resides. The prediction result is persistet as new database table in Snowflake.Example data provided from kaggle: https://www.kaggle.com/becksddf/churn-in-telecoms-dataset
1. Selection. Selects the "calls_contracts" table to use for prediction. If you haven't executed the 01b_Snowflake_ETL workflow before you can use the upper branch to create the "calls_contracts" table in Snowflake with example data.
2. Deployment and Execution. Convert the customer churn prediction model into a User-Defined Function in Snowflake.
3. Persisting. The prediction result can either be read back into KNIME or persisted as new database table within Snowflake.
Read data into KNIME
DB Reader
Read new data
CSV Reader
Apply H2O model at scale in Snowflake
Snowflake H2O MOJO Predictor (Classification)
Change connectioninformation to your Snowflake account
Snowflake Connector
Read the learned model
H2O MOJO Reader
Create db table with data
DB Writer (deprecated)
Persist prediction result in Snowflake
DB Writer (DB Data)
Select existing table with new data
DB Table Selector (deprecated)

Nodes

Extensions

  • No modules found

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: rosy
Created at: 2015-04-23
On NodePit since: 2022-04-06
Last update: 2026-07-12
Created with KNIME version: v5.11.0
Tags: SnowflakeCustomer IntelligenceCIChurnMarketing AnalyticsH2O Machine LearningMOJOsDBDatabase

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!