BUA 6110G - Predictive and Prescriptive Analytics

Credits: 4

The goal of this course is to introduce students to the dual role and the dual benefit of dependence multivariate statistical modeling techniques, which are estimating the likelihood of outcomes of interest, and delineation of the key drivers of the said outcomes of interest. The former is broadly referred to as ‘predictive analytics’ and it is geared at making forward-looking predictions regarding the chances or the magnitude of specific outcomes, while the latter is commonly referred to as ‘prescriptive analytics’ and it is geared at delineating and describing specific factors that materially contribute to either increasing or reducing the aforementioned chances and/or magnitudes, and that can be used by business managers for product design, marketing, distribution, and related purposes. The course is focused on developing rudimentary understanding of those two broad data analytical dimensions, and introducing students to some of the more widely-used predictive/prescriptive statistical techniques including linear and logistic regression models, decision trees, and more recent, machine learning focused techniques such as random forest. Prerequisite: BUA5020G or DSE5021G.