Icon

justknimeit-26

justknimeit-26
Preparing the dataSet Area Code & Churn to String via TransformationTab Model Training Model Evaluation Challenge 26: Modeling Churn Predictions - Part 4Level: EasyDescription: To wrap up our series of data classification challenges, consider again the following churning problem: a telecom company wants you to predict which customers are going to churn (that is, going to cancel their contracts) based onattributes of their accounts. The target class to be predicted in the test data is Churn (value 0 corresponds to customers that do not churn, and 1 corresponds to those who do). You have already found a good model for the problem and have alreadyengineered the training data to increase the performance a bit. Now, your task is to communicate the results you found visually. Concretely, build a dashboard that:shows performance for both classes (you can focus on any metrics here, e.g., precision and recall)ranks features based on how important they were for the modelexplains a few single predictions, especially false positives and false negatives, with our Local Explanation View component Data Visualization Read test dataRead training dataMatch original vs. predicted Churn valuesOversample churn class at each training samplepredictchurnlearn and predictchurn1 instancetile view &bar chartselect speciespreparing forvisualizationPick top #Most probableto churn Input:0 : Model as a Workflow Object1 : Data from Model Test Partition2 : Single Instance to ExplainOutput:0 : Counterfactuals Instances1 : Local Feature ImportanceCSV Reader CSV Reader Scorer (JavaScript) SMOTE Workflow Executor AutoML Row Sampling Churn Visualization Row Filter Data Prep Top k Selector Local ExplanationView Preparing the dataSet Area Code & Churn to String via TransformationTab Model Training Model Evaluation Challenge 26: Modeling Churn Predictions - Part 4Level: EasyDescription: To wrap up our series of data classification challenges, consider again the following churning problem: a telecom company wants you to predict which customers are going to churn (that is, going to cancel their contracts) based onattributes of their accounts. The target class to be predicted in the test data is Churn (value 0 corresponds to customers that do not churn, and 1 corresponds to those who do). You have already found a good model for the problem and have alreadyengineered the training data to increase the performance a bit. Now, your task is to communicate the results you found visually. Concretely, build a dashboard that:shows performance for both classes (you can focus on any metrics here, e.g., precision and recall)ranks features based on how important they were for the modelexplains a few single predictions, especially false positives and false negatives, with our Local Explanation View component Data Visualization Read test dataRead training dataMatch original vs. predicted Churn valuesOversample churn class at each training samplepredictchurnlearn and predictchurn1 instancetile view &bar chartselect speciespreparing forvisualizationPick top #Most probableto churn Input:0 : Model as a Workflow Object1 : Data from Model Test Partition2 : Single Instance to ExplainOutput:0 : Counterfactuals Instances1 : Local Feature ImportanceCSV Reader CSV Reader Scorer (JavaScript) SMOTE Workflow Executor AutoML Row Sampling Churn Visualization Row Filter Data Prep Top k Selector Local ExplanationView

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: UserID
Created at: 2022-06-29
On NodePit since: 2022-07-22
Last update: 2024-04-26
Created with KNIME version: v4.6.0
Tags: justknimeit-26

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

Try NodePit Runner!