Customer Intelligence System using Classification, Ensemble Learning & Clustering

Project Overview

This project develops a Customer Intelligence System using Machine Learning techniques to analyze country-level socio-economic data. It performs clustering, dimensionality reduction, and ensemble learning to generate meaningful business insights.

Objectives

• Data Cleaning and Preprocessing
• Exploratory Data Analysis (EDA)
• Feature Scaling
• K-Means Clustering
• DBSCAN Clustering
• Principal Component Analysis (PCA)
• Random Forest Classification
• XGBoost Classification
• Model Evaluation
• Business Insights

Technologies Used

• Python
• Pandas
• NumPy
• Matplotlib
• Seaborn
• Scikit-learn
• XGBoost
• Jupyter Notebook

Machine Learning Techniques

• Data Cleaning
• Exploratory Data Analysis
• StandardScaler
• K-Means
• DBSCAN
• PCA
• Random Forest
• XGBoost

Dataset

The project uses the Country-data.csv dataset containing socio-economic indicators such as income, GDP per capita, life expectancy, child mortality, health expenditure, imports, exports, inflation, and fertility rate.

Project Outcome

• Identified meaningful country clusters using K-Means.
• Detected outlier countries using DBSCAN.
• Visualized clusters using PCA.
• Predicted cluster membership using Random Forest and XGBoost.
• Generated actionable insights for data-driven decision making.