A Business-Analytic Approach to Identify Critical Factors in Quantitative Disciplines

Abstract

Most business students in universities across the UnitedStates find the quantitatively oriented courses challenging to comprehend the course material to a degree necessary to develop capability and confidence level to solve business problems. A determination of critical factors that influence performance in such courses is critical to designing class instructions. Instructors teaching these classes agonize over the fact that these courses are amongst the most difficult to teach as they encompass relatively harder concepts transformed into analytical skill sets with real applications to business operations that students struggle to grasp. This study employs a machine learning-based approach to determine critical success factors by analyzing the dataset of a focus course and provides some guidelines to educators for improving their teaching effectiveness. Information fusionbased sensitivity analyses on the data mining models provide an unbiased weighting scheme for the rank order of the variables that help predict the students' comprehension level.

A hybrid data analytic approach to predict college graduation status and its determinative factors

“…A flow chart of the methodology described in this section is shown in Figure 2. 116,8 2.1 Data analytic models Three data mining models (DTs, ANNs, and SVMs) are employed in the proposed hybrid approach due to their popularity in literature which stems from the fact that they have conventionally outperformed many other methods in terms of accuracy (Delen et al, 2010(Delen et al, , 2012Oztekin et al, 2009Oztekin et al, , 2011Oztekin et al, , 2013Oztekin, 2011Oztekin, , 2012Oztekin and Khan, 2014;Sevim et al, 2014;Turkyilmaz et al, 2013). Moreover, our trial-and-error experiments with these models also yielded superior results compared to the other potential prediction models such as logistic regression.…”

Can deep learning predict risky retail investors? A case study in financial risk behavior forecasting

“…To obtain a clearer view on the feature-response relationship, we employ information-fusion based sensitivity analysis (IFBSA). Originally proposed by [58], IFBSA has been used in several studies to examine feature importance through the lens of multiple classifiers [60,62,63]. IFBSA first assesses the importance of an individual feature as the percentage ratio of the model error without this feature to the model error with that feature included [62].…”