Icon

02_​Deployment_​ChurnPredictor

Exercise to deploy and inspect visually an optimized Random Forest for churn prediction.

Activity I: Deploy a Churn Predictor1. Import the optimized model2. Import the unlabelled dataset with Calls and Contracts3. Apply the model to the unlabelled data4. Create telephone ID by joining the strings of Area Code and Phone with the String Manipulation node5. Encode predictions with labels: 0 as "No Churn" and 1 as "Churn" using the Rule Engine node6. Rename probability columns: P(Churn = 1) as P (Churn) and P(Churn = 0) as P(No Churn) using the Column Rename node 7. Create an interactive data app to inspect predictions visually. Use a Bar Chart and a Tile View within the component interactive view. Activity I: Deploy a Churn Predictor1. Import the optimized model2. Import the unlabelled dataset with Calls and Contracts3. Apply the model to the unlabelled data4. Create telephone ID by joining the strings of Area Code and Phone with the String Manipulation node5. Encode predictions with labels: 0 as "No Churn" and 1 as "Churn" using the Rule Engine node6. Rename probability columns: P(Churn = 1) as P (Churn) and P(Churn = 0) as P(No Churn) using the Column Rename node 7. Create an interactive data app to inspect predictions visually. Use a Bar Chart and a Tile View within the component interactive view.

Nodes

  • No nodes found

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: roberto.cadili
Created at: 2023-07-13
On NodePit since: 2023-07-14
Last update: 2024-12-17
Created with KNIME version: v4.7.5
Tags: Churn predictionDeploymentRandom Forest

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

Try NodePit Runner!