The sample workflow codegen_workflow,
demonstrates data modelling and data scoring.
The sample workflow in this use case codegen_workflow,
comprises two distinct processes contained within a single lineage: Modeling (top) and Scoring (bottom) as shown in Figure 7-1. Both the processes use the demo data INSUR_CUST_LTV_SAMPLE
as the input data source.
Figure 7-1 The Sample Workflow - codegen_workflow
Modelling: The modeling process builds a Classification Support Vector Machine (SVM) model. It predicts whether the customer will buy insurance or not. The model coefficients are persisted to a database table for viewing. This table may provide a basis for application integration.
Scoring: The scoring process makes predictions for the customer data using the Support Vector Machine (SVM) model created by the modeling lineage. The prediction result is persisted to a database view for viewing. The view provides the following:
Predictions of the current input data. For example, if the input table is refreshed with new data, this view will automatically capture the predictions of the new data.
Basis for application integration.