Icon

KNIME_​credit

Prediction
Math Formula
Rule Engine
Loaded the dataset
CSV Reader
Column Renamer
Applied Min-Max normalization (0-1)
Normalizer
Split the data into normal transactions (fraud = 0) and fraudulent transactions (fraud = 1).
Row Splitter
Used 70% of normal transactions for training the Autoencoder
Row Sampler
Remove Target
Column Filter
Keras Network Executor
Scorer
mean_squared_error
Math Formula
Scorer (JavaScript)
Column Appender
DL Python Network Executor
Math Formula
Scorer
Rule Engine
Combines 30% validation normals (fraud=0) with all frauds (fraud=1)
Concatenate
5 neurons, ReLU activation
Keras Dense Layer
Used 30% of normal transactions for validation
Row Sampler
3 neurons (compressed representation), ReLU activation
Keras Dense Layer
Removed the fraud column from the training
Column Filter
Threshold Optimization
Input shape = 7 (one per feature)
Keras Input Layer
Keras Network Learner
Append Target
Column Appender
5 neurons, ReLU activation
Keras Dense Layer
7 neurons (reconstruct original features), sigmoid activation
Keras Dense Layer

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: bruna
Created at: 2026-05-09
On NodePit since: 2026-05-14
Last update: 2026-05-14
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!