Projects

Sales Analytics Dashboard

Interactive Power BI dashboard visualizing KPIs, revenue trends, customer segmentation, and regional performance for e-commerce data across multiple time periods.

Power BI SQL DAX Excel

Code Live Demo

Customer Churn Prediction

ML pipeline achieving 87% accuracy predicting customer churn. Includes feature engineering, model comparison (Random Forest, XGBoost, Logistic Regression), and SHAP explainability.

Python Scikit-learn Pandas XGBoost

Code Docs

COVID-19 Data Analysis

Comprehensive EDA of global COVID-19 trends — case trajectories, mortality rates, vaccination progress. Interactive charts built with Plotly and Seaborn.

Python Matplotlib Seaborn Plotly

Code Notebook

E-Commerce SQL Analytics

End-to-end SQL analysis on a 500k-row e-commerce dataset. Window functions, CTEs, cohort analysis, and customer lifetime value calculations.

SQL PostgreSQL Python

Code Report

House Price Prediction

Regression model predicting house prices with R² of 0.92. Covers data cleaning, feature selection, polynomial features, Ridge/Lasso regularization, and hyperparameter tuning.

Python Scikit-learn NumPy Jupyter

Code Notebook

HR Analytics Dashboard

Tableau dashboard tracking employee attrition, performance metrics, headcount trends, and department KPIs. Includes drill-down filters and executive summary view.

Tableau SQL Python

Code Live Demo

Open Source Contributions

I actively contribute to the developer and data science community through code, documentation, and knowledge sharing.

Community Tools

Contributing utilities and helper libraries that improve data analytics workflows across the ecosystem.

Documentation

Writing clear, comprehensive documentation to help others understand and use open source data science tools.

Bug Fixes

Identifying and resolving bugs in popular repositories to improve stability and user experience.

Feature Development

Implementing new features based on community feedback and project roadmaps in data tooling projects.