Abstract: A data analysis system utilizing custom unsupervised machine learning processes over a communications network is disclosed, the system including a repository of data, a web application deployed on a web server, the web application including a data collection interface, wherein the web application is configured for providing a graphical user interface for modifying threshold parameters of a clustering algorithm for clustering the data, executing the clustering algorithm with the threshold parameters that were modified, thereby producing a set of results, providing a graphical user interface for reviewing the set of results of the clustering algorithm and re-executing previous steps if the set of results are not useful and, executing a deep learning algorithm in a deep learning software framework on the set of results, thereby establishing relationships between the data, and providing generalizations of the data.