Undergraduate in Electronics and Communication Engineering at Gujarat Technical University, focused on machine learning engineering from data preprocessing and model selection to building explainable, deployable ML systems. I care about writing ML code that's structured, interpretable, and ready to ship, not just accurate in a notebook.

Open to Machine Learning internships, Data Science roles, and applied AI positions in predictive analytics and MLOps.

• Supervised learning: decision trees, random forests, gradient boosting (XGBoost, LightGBM, CatBoost)
• End-to-end ML pipelines: from feature engineering to model deployment
• Model explainability using SHAP for non-technical stakeholder reporting
• Applied AI on Microsoft Azure: cloud fundamentals, administration, and generative AI
• MLOps: experiment tracking, API deployment, and lightweight dashboards

Regression pipeline predicting housing prices using structured feature engineering and model comparison.

• 87% accuracy, surpassing the initial 70% target, using Linear Regression and Gradient Boosting Regressor
• Performed data cleaning, EDA, and feature engineering on housing data (bedrooms, square footage, location, waterfront, condition)
• Evaluated performance using R² score to select the best-performing model

End-to-end churn intelligence platform that goes beyond prediction into prescriptive business recommendations.

• Architected a churn prediction system using LightGBM and CatBoost, paired with SHAP-based explainability for every prediction
• Used SHAP to surface key churn drivers (usage drop, inactivity, support complaints) in a way non-technical users can understand
• Built a FastAPI/Streamlit dashboard displaying churn predictions and suggested retention actions

Languages

ML / DL

Tools and Infrastructure