Icon

BAI Group project redo1

<p>Group 4 tree based ML models for churn prediction</p>

Group 4 tree based ML models for churn prediction

Splits data 70% train / 30% test. Stratified on churn_risk_score to preserve class distribution. Fixed seed = 0 for reproducibility.
Table Partitioner
Loads raw train.csv.
CSV Reader
To append model name
Constant Value Column Appender
Decision Tree | Gain Ratio, MDL Pruning | Test Accuracy: 79.1% | Macro F1: 0.769 | Weighted F1: 0.773
Decision tree
XGBoost | Random Search, 6 Parameters | Test Accuracy: 78.2% | Macro F1: 0.772 | Weighted F1: 0.778
XG Boost
To filter extra columns
Column Filter
Cleans and prepares raw data — removes invalid rows, imputes missing values, encodes categoricals, and engineers features
Data cleansing
To filter extra columns
Column Filter
To append model name
Constant Value Column Appender
To filter extra columns
Column Filter
Random Forest | 100 Trees, Unlimited Depth | Test Accuracy: 77.6% | Macro F1: 0.762 | Weighted F1: 0.769
Random forest
To append model name
Constant Value Column Appender
Checks for missing values and outliers, and explores distribution and relationship between attributes
Data exploration

Nodes

Extensions

Links

Download

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

Download Workflow
Created by: !
Created at: 2026-02-17
On NodePit since: 2026-04-30
Last update: 2026-04-30
Created with KNIME version: v5.10.0

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

Try NodePit Runner!