Built a full end-to-end machine learning pipeline to predict surge pricing for cab rides, specifically comparing Uber and Lyft services in the New York City area. The pipeline leverages historical ride, weather, and event data to forecast price surges based on factors such as time, location, weather, and demand patterns. Utilized multiple machine learning algorithms—including Random Forest, XGBoost, and Gradient Descent-based models—and selected the best-performing model for accurate surge price prediction. The project emphasizes MLOps principles with MLflow for experiment tracking, DVC for data versioning, and Docker for reproducible deployments.