My Projects

Heart Disease Classification

Using machine learning to predict the presence of heart disease from patient data.

• Tools: Python, XGBoost, Scikit-learn, Pandas, Matplotlib, Seaborn
• Goal: Classify whether a patient has heart disease based on clinical measurements
• Outcome: Achieved an F1 score of 0.84 on the validation set and 0.75 on the holdout set
• Read the full report

Bike Rentals Prediction

Forecasting pedal power with deep learning and pandemic-aware features.

• Tools: Python, Keras, Scikit-learn, Pandas, Matplotlib
• Goal: Predict hourly bike rentals using time-based and COVID-era features
• Outcome: Achieved 89% R² accuracy with a dropout-regularized neural net
• Read the full report

Housing Price Prediction

Unlocking the mystery of what makes homes expensive (besides the granite countertops).

• Tools: Python, Jupyter, Seaborn, XGBoost, Random Forest
• Goal: Used machine learning to uncover which features drive housing prices — from luxury scores to longitude
• Outcome: Our model predicted prices with 91% accuracy (R²), blending interpretability and performance
• Read the full report

Pawesome Pet Services Database Redesign

• Tools: MySQL Workbench, ERD modeling
  
• Goal: Normalize and restructure the schema to better manage pet services and appointments
  
• View the full write-up