The vast majority of the literature related to the empirical estimation of retention models includes a discussion of the theoretical retention framework established by Bean, Braxton, Tinto, Pascarella, Terenzini and others (see Bean, 1980; Bean, 2000; Braxton, 2000; Braxton et al, 2004; Chapman and Pascarella, 1983; Pascarell and Ternzini, 1978; St. John and Cabrera, 2000; Tinto, 1975) This body of research provides a starting point for the consideration of which explanatory variables to include in any model specification, as well as identifying possible data sources. The literature separates itself into two major camps including research related to the hypothesis testing and the confirmation or empirical validation of theoretical retention models (Herzog, 2005; Ronco and Cahill, 2006; Stratton et al 2008) vs. research specifically focused on the development of applied predictive models (Miller, 2007; Miller & Herreid, 2008; Herzog, 2006; Dey & Astin, 1993; Delen 2010; Yu et al, 2010). Literature indicates that data mining or algorithmic approaches to prediction can provide superior results vis-à-vis traditional statistical modeling approaches (Delen et al, 2004; Sharda and Delen, 2006; Delen et al, 2007; Kiang 2007; Li et al 2009). However, little research in higher education has focused on the employment of data mining methods for predicting retention (Herzog, 2006).
