Icon

01 Capturing segments - Development training workflow

Training workflow. This workflow accesses the training data from a file, splits and preprocesses it, and trains the credit scoring model.

Preparing a Prediction Workflow for Deployment

Train a credit scoring model

This workflow accesses the training data from a file, splits and preprocesses it, and trains the credit scoring model. The preprocessing and predicting parts are captured and saved as an automatically created prediction workflow.

Apply preprocessing and apply model (capture nodes)
Preprocess data and train model (capture source objects)
Remove errors:RevolvingUtilizationOfUnsecuredLines > 10
Row Filter (deprecated)
75% training 25% test
Table Partitioner
Scorer
XGBoost Tree Ensemble Learner
ConvertMonthly Income
String to Number
Remove errors:RevolvingUtilizationOfUnsecuredLines > 10
Row Filter (deprecated)
XGBoost Predictor
Historical customer data for existing customers
Table Reader
Use medianMonthly Incomeinstead of missingvalues
Missing Value
Capture Workflow End
Capture Workflow Start
ConvertMonthly Income
String to Number
Use medianMonthly Incomeinstead of missingvalues
Missing Value (Apply)
Workflow Writer

Nodes

Extensions

Links