Project Overview

This project focuses on customer segmentation using various unsupervised machine learning techniques. The goal is to group customers into meaningful clusters based on their purchasing behavior and demographic attributes, which can help businesses personalize marketing strategies, improve customer engagement, and optimize sales.

The project explores different dimensionality reduction and clustering techniques to analyze the dataset and compare their effectiveness in separating distinct customer groups.

Methods & Techniques Used

Data Preprocessing

• Handling missing values
• Feature scaling (StandardScaler / MinMaxScaler)
• Encoding categorical features\

Dimensionality Reduction

• PCA (Principal Component Analysis)
• Kernel PCA (Polynomial & RBF kernels)
• t-SNE (t-distributed Stochastic Neighbor Embedding)

Clustering Algorithms

• K-Means
• DBSCAN (Density-Based Spatial Clustering of Applications with Noise)

Evaluation & Visualization

• Explained variance ratios from PCA
• Scatter plots of reduced dimensions
• Cluster separability analysis

----> The Dataset used in this mini project was taken from kaggle -- Customer segmentation DataSet