Fraud_Detection_Quantile_Method_Deployment
Fraud Detection: Quantile Method Deployment
This workflow shows the deployment of using Quantile Method. We read in pre-trained normalization model, outlier model, and a test transaction. After this, we apply the normalizer model and the quantile scalar on the test data. The outliers are labeled, and we 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 Quantile Method on new data by performing the following steps:
1. Read the Models and new Data
2. Deploy the Normalization Model on the new transaction
3. Mark Outliers
Nodes
Extensions
Links
- No links available