In recent years, rapid advancement has taken place in computing technology that allows institutional researchers to efficiently and effectively address data of increasing volume and structural complexity (Luan, 2002). In this chapter, the authors propose a new data analytical technique, Bayesian belief networks (BBN), to add to the toolbox for institutional research. BBN is a Bayesian probabilistic approach to nonlinear classification problems that is applicable to situations in which large numbers of data are available, expert inputs may be used in addition to the objective information in the data, a large number of qualitative and quantitative variables have potential impact, and the nature of the analysis is exploratory and, most likely, explanatory. Examples of such problems include identifying factors related to effective student retention, investigating factors contributing to faculty turnover, and pinpointing critical parameters in classifying peer institutions. The authors discuss the advantages of BBN in comparison to conventional statistical procedures that were developed prior to the 1970s for hypothesis-based analyses, and later exemplify an application of BBN by analyzing a database and classifying a national sample of faculty members to the right Carnegie type of their institution. (Contains 5 tables and 3 figures.)