Icon

Projeto_​Final_​MABD

Keras Autoencoder for Fraud Detection - Training

This workflow trains an autoendcoder model to detect fraudulent transactions.

Keras Autoencoder Architecture
Data Preprocessing
Training the Autoencoder
Optimizing threshold K
Final Performance
Data Cleaning and Preparation

2/3 of negatives for training
Table Partitioner
1/3 of negativesand all positivesfor validation
Concatenate
Min-max normalization
Normalizer
Variable to Table Row
Table Writer
Normalizer (Apply)
Shape: 20
Keras Input Layer
Remove missing values
Missing Value
Units: 12Activation: Sigmoid
Keras Dense Layer
Extract Transaction Time Features
Date&Time Part Extractor
Units: 24Activation: Sigmoid
Keras Dense Layer
Convert Transaction Date
String to Date&Time
Units: 12Activation: Sigmoid
Keras Dense Layer
Encode Previous Transactions
Rule Engine
Units: 4Activation: Sigmoid
Keras Dense Layer
Weekend TransactionClassification
Rule Engine
10 % for validation
Table Partitioner
Units: 20Activation: Sigmoid
Keras Dense Layer
Units: 24Activation: Sigmoid
Keras Dense Layer
Create Dummy Variables
One to Many
Math Formula
Train with Loss function=MSE Optimizer=Adam
Keras Network Learner
Write model
Keras Network Writer
Create Fraud Label
Rule Engine
Scorer (JavaScript)
Generate Counter Variable
Counter Generation
Column Renamer
Group Transactions by Location
GroupBy
Filter Relevant Variables
Column Filter
Apply network
Keras Network Executor
Create Transaction Status
Rule Engine
Join Transaction Location Data
Joiner
Format Card Expiration Date
String Manipulation
Classifytransactions based onthreshold
Rule Engine
Create Year-Month Feature
Math Formula
Class
Number to String
Detect Expired Cards
Rule Engine
Excel Reader
Top:Class = 0
Row Splitter
Convert Date Features to Number
String to Number
Graphs
Threshold Optimization
Normalizer (Apply)
Normalizerfor deployment
Model Writer
Graphs_Flag

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: Maarit Laukkanen
Created at: 2019-02-25
On NodePit since: 2026-05-16
Last update: 2026-05-16
Created with KNIME version: v5.11.0
Tags: autoencoderKerasneural networkdeep learningencoderdecoderreconstructioncredit card datafraud detectionanomaly detectionmodel evaluationbankingcredit cardfraudcybersecurity

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!