Non-parametric classifiers overcome the reliance on statistical assumptions of parametric methods and have been noted by several studies to consistently produce higher classification accuracies than their parametric counterparts (Friedl and Brodley, 1997; Hansen et al., 1996; Mondal et al., 2012; Murthy et al., 2003; Pal and Mather, 2003). Frequently used algorithms in this category include artificial neural networks (ANN), support vector machines (SVM) and decision trees (DT), which are all implementable with freely available software packages (e.g. R, Python). The disadvantage with which many of these algorithms come is that they tend to be computationally demanding, and deliver results more slowly than parametric algorithms. Nonetheless, non-parametric algorithms should always be considered due to their superior accuracies.