Icon

KNIME_​PROJFinal

<p>Fraud Detection in Credit Cards.<br><br>Link dataset: https://drive.google.com/drive/folders/1ug7tFHToafCralMk3KC-UTh_5_fnruEh?q=sharedwith:public%20parent:1ug7tFHToafCralMk3KC-UTh_5_fnruEh</p>

Fraud Detection in Credit Cards.

Link dataset: https://drive.google.com/drive/folders/1ug7tFHToafCralMk3KC-UTh_5_fnruEh?q=sharedwith:public%20parent:1ug7tFHToafCralMk3KC-UTh_5_fnruEh

Data Preprocessing
Training the Autoencoder
Optimizing threshold K
Final Performance
Keras Autoencoder Architecture
DBSCAN Model

Exploration Data

Random Forest

70% of negativesfor training
Table Partitioner
30% of negativesand all positivesfor validation
Concatenate
Min-max normalization
Normalizer
Normalizer (Apply)
Shape: 7
Keras Input Layer
Units: 5Activation:Sigmoid
Keras Dense Layer
Units:15Activation: Sigmoid
Keras Dense Layer
Units: 7Activation: Sigmoid
Keras Dense Layer
80% of train
Table Partitioner
Units: 8Activation:Sigmoid
Keras Dense Layer
10 % for validation
Table Partitioner
Units: 15Activation:Sigmoid
Keras Dense Layer
Scorer
Verification
Statistics
Normalizer
Train with Loss function=MSE Optimizer=Adam
Keras Network Learner
Target: fraud
Random Forest Learner
To define fraud
Rule Engine
Random Forest Predictor
Units: 8Activation: SIgmoid
Keras Dense Layer
5% of data
Row Sampler
Normalizer
Configuration Eclidean
Numeric Distances
DBSCAN
Apply network
Keras Network Executor
Fraud
Number to String
Read credit card data
CSV Reader
Normalizer (Apply)
Classifytransactions based onK
Rule Engine
Fraud
Number to String
ROC Curve
Definig Noise
Rule Engine
Top:fraud = 0
Row Splitter
Scorer
Optimizing K
Threshold Optimization
Scorer
Convert 'fraud' column to string for visualization
Number to String
Normalizer (Apply)
Number to String
Class distribution: Fraud vs. Non-Fraud
Bar Chart
Distribution of numeric variables
Box Plot
Verification
Statistics
Distribution of ratio_to_median_purchase_price by class
Box Plot
Calcule MSE
Math Formula
Min-Max normalization of numerical features
Normalizer
Descriptive statistics of normalized features
Statistics

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: elodi
Created at: 2026-05-16
On NodePit since: 2026-05-17
Last update: 2026-05-20
Created with KNIME version: v5.11.0

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

Try NodePit Runner!