Fraud Detection: Distribution Method Deployment
This workflow shows the deployment of using a Distribution Method. We read in pre-trained normalization PMML model and test data and apply the model to filter out distribution tails as potential outliers. It labels these outliers and will use a Case Switch to decide whether we notify if there is a fraudulent transaction or not.
This workflow demonstrates how we can use the Distribution Method on new data by performing the following steps:
1. Read the model and new data
2. Deploy the Normalization PMML Model on the new transaction
3. Mark Outliers
This workflow shows the deployment of using a Distribution Method. We read in pre-trained normalization PMML model and test data and apply the model to filter out distribution tails as potential outliers. It labels these outliers and will use a Case Switch to decide whether we notify if there is a fraudulent transaction or not.
This workflow demonstrates how we can use the Distribution Method on new data by performing the following steps:
1. Read the model and new data
2. Deploy the Normalization PMML Model on the new transaction
3. Mark Outliers