Fraud Detection: Model Deployment

This workflow, the deployment workflow, reads the trained model, as well as the new transaction and applies the model to classify it. Like in the training workflow we use a Rule Engine node to apply the custom threshold. In case a transaction is classified as fraudulent the workflow sends an email to the fraud department.


This is a companion discussion topic for the original entry at https://kni.me/w/LB4lY6Y7CLAcgYon