I conducted a data-driven study on predicting and understanding hair loss using a combination of data visualization and machine learning. The project explored how factors such as age, stress, medical conditions, and nutritional deficiencies contribute to hair loss. Using techniques like logistic regression, random forest, and clustering, I analyzed patterns, identified key risk factors, and provided actionable recommendations for prevention and early intervention.
0
3
This project explores hospital efficiency using real-world health data. It visualizes key metrics such as average length of stay, cost per discharge, severity of illness, and patient outcomes across multiple hospitals. The dashboard helps identify trends, compare performance, and support data-driven decisions to improve healthcare delivery and resource use.
0
2
Developed a machine learning model to predict diabetes risk using the Pima Indians dataset. Cleaned and analyzed patient health data, built Random Forest and Logistic Regression models, and identified key predictors such as glucose, BMI, and age. Created interactive visualizations to uncover insights and provide recommendations for early diabetes detection.
0
4
Developed a data-driven gym operations dashboard that analyzed membership trends, attendance patterns, and revenue data to generate actionable insights. The project helped gym owners and managers optimize resource allocation, identify peak hours, improve member retention, and make smarter business decisions based on real-time analytics.