Shalini Mehta

Developed an end-to-end Health & Fatigue Prediction System using Machine Learning algorithms including Random Forest and XGBoost for multiclass fatigue classification. Performed data cleaning, preprocessing, feature engineering, label encoding, outlier detection (IQR), and feature scaling on physiological and operational datasets. Designed predictive models to classify fatigue levels into Low, Moderate, and High risk categories, enabling data-driven decision support.

Data Science Intern at DRDO (2026-01 – 2026-02)

• Developed an end-to-end Health & Fatigue Prediction System using Machine Learning algorithms including Random Forest and XGBoost for multiclass fatigue classification.
• Performed data cleaning, preprocessing, feature engineering, label encoding, outlier detection (IQR), and feature scaling on physiological and operational datasets.
• Designed predictive models to classify fatigue levels into Low, Moderate, and High risk categories, enabling data-driven decision support.
• Applied stratified train-test splitting, hyperparameter tuning, and model optimization techniques to improve prediction reliability and reduce overfitting.

Bachelor of Technology in Artificial Intelligence and Data Science – Dr. Akhilesh Das Gupta Institute of Professional Studies (2023-08)