You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
AI-powered prediction of in-hospital mortality and 30-day readmission using MIMIC-III clinical data. Combines structured features and ClinicalBERT embeddings with XGBoost/CatBoost Best Performance models for accurate, explainable healthcare forecasting.
Applied K-Means clustering on Mall Customers dataset with PCA for dimensionality reduction. Cluster labels were added to the dataset and used to train Random Forest and LightGBM classifiers to predict customer segments on new data.
Developed a deep learning-based crime classification system using data preprocessing, model optimization, and computer vision, with a Flask web app for real-time crime incident analysis and prioritization.