Project Overview
This project aims to segment customers based on their spending behavior and demographic information using clustering techniques. The workflow consists of data preprocessing, exploratory data analysis (EDA), and implementing K-Means and Hierarchical clustering.
- Data Preprocessing
Handle missing values and format date fields.
Encode categorical variables (Education, Marital_Status).
Standardize numerical features to ensure optimal clustering performance.
- Exploratory Data Analysis (EDA)
Analyze spending behavior using boxplots.
Generate a correlation heatmap to explore feature relationships.
- Clustering Techniques
A. K-Means Clustering
Use the Elbow Method to determine the optimal number of clusters.
Fit the K-Means algorithm (k=4) and visualize clusters using pair plots.
B. Hierarchical Clustering
Apply Ward’s method to form clusters.
Generate a Dendrogram (50 samples) for better readability and interpretation.