Icon

DBSCAN- Fraud Detection

2 workflows in this folder and its subfolders

Icon
01_​Training DBSCAN for Fraud Detection

This workflow uses the DBSCAN clustering algorithm to detect fraud by identifying outliers in credit card transaction data. Density-based spatial clustering of applications with noise (DBSCAN) is a unsupervised clustering algorithm that works well with data that does not vary significantly across di…

Icon
02_​Deployment DBSCAN for Fraud Detection

We read in all our saved models and tables to prepare for the similarity search. Read the new transaction and add it to the normalize (apply) with the saved model. Perform the similarity search and classify whether or not the transaction is potentially fraudulent or not. If it is, an email can be se…