• Developed a dynamic clustering model using market features to optimize revenue for 589,000+ markets, replacing the static approach.• Executed extensive data cleaning and EDA on a dataset of 4.98 million rows using sklearn to identify key markets and demand patterns.• Engineered market-specific features such as service types, market circuitry, and passenger share to logically cluster similar markets.• Applied multiple clustering methods, including K-Means, Agglomerative and DBSCAN, determining K-Means as the optimal solution.