Abstract: Technologies for unsupervised data classification include a computing device that generates a high dimensional profile for each column of a data store that is indicative of topological features of the column. The computing device also analyzes each column using multiple predetermined profiling rules and generates an initial classification for the columns based on profiling rule results. The initial classification may be applied to related columns based on clustering of the columns using the high dimensional profile. The computing device may train a machine learning model based on the initial classification and the high dimensional profile. Input features for training may include the profiling rule results and the high dimensional profile. Classifications may be provided to client devices via a predetermined interface. Other embodiments are described and claimed.