Strong electron correlations often lead to emergent magnetic behavior in materials. Predicting such magnetic properties is essential for advancing technologies in spintronics, data storage, and quantum computing. However, traditional methods - whether experimental techniques or density functional theory (DFT) calculations - are often complex, time-consuming, or unreliable in strongly correlated systems. This project aims at building machine learning models to predict the magnetic ordering of inorganic compounds using chemical, structural, electronic, and thermodynamic descriptors. By leveraging existing materials databases (The Materials Project + Bilbao Crystallographic Server MAGNDATA), our goal is to build a ML model that offers a faster, data-driven alternative for accelerating the discovery and design of novel magnetic materials. Our results represent a step forward in tackling the grand challenge of magnetism.