The classification of astronomical objects plays a crucial role in advancing our quest for extraterrestrial life and deepening our understanding of the universe's origins. The task is challenging due to the typically grainy nature of images of galaxies, stars, and quasars, which makes distinguishing their features with the naked eye difficult.

This necessitates the training of sophisticated algorithms capable of accurately discerning these celestial bodies. Given the subtle differences in the appearance of stars, quasars, and galaxies to human observers, it is essential for these algorithms to classify and predict with high precision. Accurate classification is pivotal, as it could be the key to identifying Earth-like exoplanets.

This project aims to develop and evaluate three classification algorithms – Random Forest, XGBoost, and a Convolutional Neural Network (CNN) – for their effectiveness in differentiating between these types of astronomical objects. The focus is on assessing the performance and practical utility of these widely used machine learning algorithms in the context of astronomical object classification.