Three broad topics are examined: Machine learning, Cybercrime, and Network Intrusion Detection. The intersection of these three topics forms the platform for this case study. As threat actors engaged in cybercrime are constantly seeking new avenues to exploit attack vectors, those responsible for securing those spaces need to leverage all resources available. The ubiquity of networks and the scale of traffic data associated with them make an excellent platform by which the advancements in machine learning can be applied to identify and defend against such attacks. The following case study evaluates machine learning classification methods to identify anomaly based network intrusions. Specifically, machine learning methods of multiple logistic regression, support vector machines, and artificial neural networks were evaluated, and determinations were made on their performance. This study found that of the methods listed above, the support vector machine algorithm, when fit on a test set of the processed data, performed optimally.