Icon

FINAL

1. DATA PREPROCESSING AND EXPLORATORY ANALYSIS

3. CLUSTERING

2. FEATURE ENGINEERING

MEA 2025/2026 — Group Project — NEW Super Markets International

Group: GROUP BW

Members:

4. Predictive modeling

Engagement lens

Customer-value lens

Product-mix lens

Percentage_Others
Math Formula
String Replacer
For Internet values are above 100 detected (It cant be as its a percentage)
Histogram
Monetary is strongly right skewed
Histogram
We reverse the scaling
Denormalizer
Segments profile
GroupBy
Percentage_Canned
Math Formula
Training dataset
Excel Reader
Renames cluster_2
String Replacer
Percentage_Beverages
Math Formula
Percentage_Frozen
Math Formula
Renames cluster_0
String Replacer
Renames cluster_1
String Replacer
Percentage_Perishables
Math Formula
Normalizer
Linear Correlation
Percentage_Frozen
Math Formula
Number to String
Decision Tree Learner
Shows us that Gender contains missing values
Bar Chart
Table Partitioner
Percentage_Canned
Math Formula
Helps us detect a 0 in Education
Bar Chart
Bar Chart
Helps us detect a missing value in Marital Status
Bar Chart
Bar Chart
Change the 0 in Education with the most occured variable
String Replacer
Table View
Cap the value greater than 100 in internet
Math Formula
Column Filter
Monetary X income
Scatter Plot
Decision Tree Predictor
Normalizer
Scorer
Table Partitioner
Table Manipulator
MultiLayerPerceptron Predictor
Percentage_Beverages
Math Formula
Percentage_Perishables
Math Formula
Histogram
Column Filter
Silhouette Coefficient
Statistics
Silhouette Coefficient
Table Manipulator
Column Filter
Numeric Outliers
Silhouette Coefficient
Missing Value
Silhouette Coefficient
Verified
Statistics View
Silhouette Coefficient
Impute whats left
Missing Value
Silhouette Coefficient
Stron Skewness detected in Recency
Histogram
Numerical profile: mean, std, missing counts per variable
Statistics
Column Filter
Correlation Insights
Linear Correlation
CUSTID column was corrected
RowID
k-Means with k=4
k-Means
Histogram
k-Means with k=5
k-Means
Cap the value greater than 100 in internet
Rule Engine
k-Means with k=5
k-Means
Bar Chart
k-Means with k=3
k-Means
Numeric Outliers
k-Means with k=3
k-Means
k-Means with k=4
k-Means
Table Manipulator
k-Means with k=4
k-Means
k-Means with k=3
k-Means
Color each cluster for further visualisation
Color Manager
Numeric Outliers
k-Means with k=5
k-Means
Statistics
Silhouette Coefficient
We reverse the scaling
Denormalizer
Column Filter
Color each cluster for further visualisation
Color Manager
confirms cluster separation
Distance Matrix Calculate
Missing Value
Silhouette Coefficient
Renames cluster_0
String Replacer
Statistics
Top overall score
Silhouette Coefficient
Excel Writer
Segments profile
GroupBy
Statistics
Renames cluster_2
String Replacer
Normalizer
Renames cluster_1
String Replacer
Math Formula (Multi Column)
confirms cluster separation
Distance Matrix Calculate
k-Means
Color each cluster for further visualisation
Color Manager
We reverse the scaling
Denormalizer
confirms cluster separation
Distance Matrix Calculate
Renames cluster_0
String Replacer
Segments profile
GroupBy
Renames cluster_2
String Replacer
Renames cluster_1
String Replacer
Bar Chart
Bar Chart
Numerical profile: mean, std, missing counts per variable
Statistics
Stron Skewness detected in Recency
Histogram
We uploaded the dataset
Excel Reader
Table Manipulator
Monetary X income
Scatter Plot
Change the 0 in Education with the most occured variable
String Replacer
Column Filter
CUSTID column was corrected
RowID
ROC Curve
Correlation Insights
Linear Correlation
Changes made on Income , Gender and Marital Status
Missing Value
Lift Chart (JavaScript) (legacy)
Lift Chart (JavaScript) (legacy)
ROC Curve
Scorer
RProp MLP Learner
Correlation Filter
Table View
Avg_Visit
Math Formula
Shows us that Gender contains missing values
Bar Chart
Helps us detect a missing value in Marital Status
Bar Chart
Helps us detect a 0 in Education
Bar Chart
String Replacer
Table View
Monetary is strongly right skewed
Histogram
String Replacer
For Internet values are above 100 detected (It cant be as its a percentage)
Histogram
String Replacer
String Replacer
String Replacer
Income_Share
Math Formula
Churn_Rate
Math Formula
Avg_Visit
Math Formula
String Replacer
Percentage_Others
Math Formula
String Replacer
Income_Share
Math Formula
String Replacer
String Replacer

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: azzag
Created at: 2026-05-24
On NodePit since: 2026-05-30
Last update: 2026-06-21
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!