Developed an end-to-end machine learning pipeline to predict airfoil noise levels using a modified version of the NASA Airfoil Self-Noise dataset. The project involved data extraction, transformation, and loading (ETL) to clean and preprocess the dataset, followed by the creation of a robust machine learning model to predict sound levels. Key tasks included data cleaning, model training and evaluation, and model persistence for future use. This project improved data processing efficiency and predictive accuracy.