Machine learning model to predict diabetes risk from clinical features, optimized for recall in a medical screening context.

Dyslipidemia, a condition with abnormal lipid levels in the blood, significantly increases the risk of cardiovascular diseases like heart attacks and strokes. This project aims to build accurate models for predicting dyslipidemia using both machine learning (ML) and deep learning (DL) techniques. The primary focus is on maximizing recall to minimiz

End-to-end predictive analytics pipeline for student retention using imbalanced academic data, stacked ML models, recall-optimized decision thresholds, and fairness-aware evaluation with cost–benefit analysis.

Built a machine learning pipeline to detect fraudulent credit card transactions using real-world data (1M+ rows). Explored fraud patterns, validated key hypotheses, and optimized models like KNN, Random Forest, and SVM with 98%+ recall. Strong focus on data insights & impact.

Developed an ensemble ML classification model to predict U.S. visa case outcomes (Certified vs Denied) using applicant and employer attributes. Performed EDA, sampling, and model tuning (Random Forest, Gradient Boosting, XGBoost) to improve decision efficiency and identify key policy drivers like education, experience, and wage trends.

📊 Identify at-risk students with a predictive analytics system that ensures fair, effective retention strategies across diverse demographic groups.