Icon

Project Pertama

MARKET SEGMENTATION LOGIC

DATA INGESTION & CLEANING

DATA INGESTION & CLEANING

DATA INGESTION & CLEANING

PRODUCT PERFORMANCE ANALYSIS

DATA ENRICHMENT & FINAL REPORTING

Data Ingestion: Loading the raw beauty cosmetics dataset from CSV format for processing
CSV Reader
Text Normalization: Stripping the 'ml' suffix from the Product_Size column to prepare it for numerical conversion
String Manipulation
Data Imputation: Handling null values by applying Mean to numerical columns and labeling empty categories as 'Unknown'
Missing Value
Type Casting: Converting the Product_Size column from String to Double/Number to enable mathematical operations
String to Number
Feature Engineering: Calculating a new metric 'Price per Unit' to normalize product pricing for better comparison
Math Formula
Market Segmentation: Categorizing products into Premium, Mid-Range, and Budget tiers based on Price_USD thresholds to analyze consumer segments
Rule Engine
Quality Assessment: Categorizing products into 'Best Seller', 'Average', or 'Underperform' based on customer ratings to identify high-performing items
Rule Engine
Data Minimalism: Retaining only the final relevant columns for the business report to ensure output clarity
Column Filter
Data Enrichment: Merging the master dataset with the Brand Tier reference table to provide business context for each product
Joiner
Formatting: Renaming technical aggregation labels (e.g., Mean, Sum) to user-friendly titles for stakeholders
Column Renamer
Reference Table Creation: Computing the average price per Brand to serve as the baseline for market segmentation
GroupBy
Output Delivery: Exporting the cleaned master table containing all product-level details and business categories to Excel
Excel Writer
Business Logic: Classifying brands into 'Luxury', 'Mid-Range', or 'Mass Market' based on predefined price thresholds
Rule Engine
Data Integrity: Removing duplicate records based on Product Name and Brand to ensure accurate review counts
Duplicate Row Filter
Aggregation: Summarizing average Ratings and total Reviews by Category and Brand Tier for management reporting
GroupBy
Data Delivery: Exporting the final processed report to an Excel file (.xlsx) for business distribution
Excel Writer
Text Normalization: Stripping the 'ml' suffix from the Product_Size column to prepare it for numerical conversion
String Manipulation
Type Casting: Converting the Product_Size column from String to Double/Number
String to Number
Data Imputation: Handling null values by applying Mean to numerical columns and labeling empty categories as 'Unknown'
Missing Value
Data Integrity: Removing duplicate records based on Product Name and Brand to ensure accurate review counts
Duplicate Row Filter

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: AFIFAH RAHMAWATI
Created at: 2026-01-29
On NodePit since: 2026-01-30
Last update: 2026-02-07
Created with KNIME version: v5.9.0

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

Try NodePit Runner!