Particle physics research requires collecting massive amounts of particle collision data. In this data one can extract evidence for the production and decay of new, interesting types of matter. However, the signature left by these new, interesting particles is obscured by other less interesting processes; it is a major challenge in particle physics to efficiently and reliably distinguish the interesting “signal” among the mundane “background”. The purpose of this research project is to explore machine learning methods that can be used to increase our sensitivity to these novel signatures. In order to conduct our research, we will utilize simulated data samples from the LHC and the output of the Compact Muon Solenoid (CMS) detector, for both the interesting signals and the mundane background processes. We will then perform novelty detection analysis on the simulated data using several different machine learning algorithms, and compare their relative performance. Such machine learning techniques are becoming popular in particle physics research; the level of investigation of this study will help lay the foundation upon which future work may build. Through our research we have the potential to determine an effective machine learning algorithm that could be used to discover dark matter, gravitons, or answers to other underlying questions of the universe.