Data Scientist

Built regression models for ETA prediction and compliance-gap forecasting with R² above 0.85, as well as classification models for product scoping, user classification, and QC accuracy prediction with 85–90% accuracy. Trained Random Forest, XGBoost, and Logistic Regression models using cross-validation, hyperparameter tuning, and drift monitoring.

Developed Python and Alteryx ETL workflows that consolidated multi-source data, including ServiceNow API integrations, reducing manual processing by more than 150 hours per quarter. Implemented feature engineering, standardized model evaluation, and created dashboards covering report complexity, compliance risk, and product licensability.

Developed a predictive workload allocation model for assigning reports to QC analysts based on performance and skill, improving QC pass rates and reducing rework cycles. Received a Spot Award for a production-grade machine learning and automation solution.

Developed an automated resume screening model that achieved 85% accuracy.

Built a real-time mask detection model that achieved 97% accuracy using Python, machine learning, and deep learning techniques.

Performed data preprocessing and exploratory data analysis for machine learning projects.

Developed supervised and unsupervised machine learning models using Python.

Bachelor of Technology in Electronics and Electrical Engineering with a minor in Software Engineering.