Icon

02_​Autoencoder_​for_​Fraud_​Detection_​Deployment

Keras Autoencoder for Fraud Detection - Deployment

This workflow applies a trained autoencoder model to detect fraudulent transactions.





Reading data, parameters, andnetwork The Fraud Detector - data normalization - reproduction of data by autoencoder - MSE calculation - Applying threshold Taking ActionsIF trx is legitimate => do nothingIF trx is fraud candidate => send email to owner Read Keras modelcreditcard_autoencoder.h5creditcard_deployment.csvnormalizer.modelReconstructdeployment datawith autoencoderDefine outliers bythe best threshold forreconstruction errorsend email to ownerport 0 => trx legitport 1 => fraud?threshold.table Keras NetworkReader File Reader Model Reader Normalizer (Apply) Keras NetworkExecutor Rule Engine Send Email Table Rowto Variable CASE SwitchVariable (Start) Table Reader Table Rowto Variable Math Formula Reading data, parameters, andnetwork The Fraud Detector - data normalization - reproduction of data by autoencoder - MSE calculation - Applying threshold Taking ActionsIF trx is legitimate => do nothingIF trx is fraud candidate => send email to owner Read Keras modelcreditcard_autoencoder.h5creditcard_deployment.csvnormalizer.modelReconstructdeployment datawith autoencoderDefine outliers bythe best threshold forreconstruction errorsend email to ownerport 0 => trx legitport 1 => fraud?threshold.table Keras NetworkReader File Reader Model Reader Normalizer (Apply) Keras NetworkExecutor Rule Engine Send Email Table Rowto Variable CASE SwitchVariable (Start) Table Reader Table Rowto Variable Math Formula

Nodes

Extensions

Links