Learning a more distributed representation of the input feature space is a powerful method to boost the performance of a given predictor. Often this is accomplished by partitioning the data into homogeneous groups by clustering so that separate models could be trained on each cluster. Intuitively each such predictor is a better representative of…

Many educational researchers have identified issues on classifying schools and some have made use of ad-hoc classification systems in their analyses; however, these solutions are generally one-dimensional, which prohibits them from capturing the full breadth of variation among schools. To understand the amount of variation that exist in schools…