Icon

Inside Data Bodensee Vol 3 - Churn Prediction

The final workflow that was interactively built during the Inside Data Bodensee Vol 3 event. It highlights various features of KNIME Analaytics Platform while building a predictive model for churning telecommunication costumers.

Read data aboutindividual customersfrom two sources Inspect descriptivestatistics of input data Join data aboutindividual customersfrom different tablesbased on uniqueentries in Phonecolumn Some data filter to remove customers witha too short Account Length. Also, convertChurn column from numerical to numinalfor model building Visualize two properties in Scatter plot with the data pointscolored according to their entries in the Churn column Build classification model to predict if a customer churns or not based on their call statisticsand other properties ContractData.csvCallsData.xlsJoin data based onPhone numbersAccount Length < 5Node 9Node 10Split into trainingand test dataApply model totest dataTrain modelEvaluate modelperformance CSV Reader Excel Reader Statistics Statistics Joiner Row Filter Number To String Color Manager Scatter Plot Partitioning Decision TreePredictor DecisionTree Learner Decision Tree View Scorer Read data aboutindividual customersfrom two sources Inspect descriptivestatistics of input data Join data aboutindividual customersfrom different tablesbased on uniqueentries in Phonecolumn Some data filter to remove customers witha too short Account Length. Also, convertChurn column from numerical to numinalfor model building Visualize two properties in Scatter plot with the data pointscolored according to their entries in the Churn column Build classification model to predict if a customer churns or not based on their call statisticsand other properties ContractData.csvCallsData.xlsJoin data based onPhone numbersAccount Length < 5Node 9Node 10Split into trainingand test dataApply model totest dataTrain modelEvaluate modelperformanceCSV Reader Excel Reader Statistics Statistics Joiner Row Filter Number To String Color Manager Scatter Plot Partitioning Decision TreePredictor DecisionTree Learner Decision Tree View Scorer

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: helfrich
Created at: 2021-01-20
On NodePit since: 2021-01-23
Last update: 2024-11-21
Created with KNIME version: v4.3.0

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

Try NodePit Runner!