The European Organization for Nuclear Research also known as CERN houses the Large Hadron Collider (LHC), which plays a role in scientific exploration. It allows us to delve into the world of particles and the forces that shape our universe. Among the LHC endeavors is the ATLAS experiment, which offers a perspective on proton collisions and provides us with a wealth of valuable data. Our research focuses on utilizing machine learning models to simulate these collisions within the ATLAS experiment. This innovative approach aims to uncover hidden patterns and relationships within the realm pushing beyond the boundaries set by the Standard Model. In this paper, we present an analysis of data using machine learning techniques revealing unknown correlations and patterns among subatomic particles. Moving forward our research will involve expanding the dataset through data collection from LHC experiments refining our machine learning models and conducting investigations to validate these proposed relationships, among subatomic particles.