Abstract:

Early student risk detection and amelioration continue to challenge the management education community especially in light of COVID-19. . The goal of identifying students at academic risk early in the matriculation process is not new. Specifically, Seidman proposed in the late 1990s that both early detection and continuous interventions were keys to student retention. Recent data suggest that machine learning-based predictive models can provide automatic and timely student assessments, which allow for both the detection of students at risk and the implementation of appropriate intervention initiatives. The empirical results from the current study, which included both student demographic and performance data, suggest that machine learning-based knowledge discovery can be used to design customized intervention strategies. Actionable knowledge discovery decision trees have seen increased use in the customer relationship management field to identify specific actions that would transform a fickle customer to one loyal to the organization. The approach, as applied to students, is to develop a decision tree that reports the risk dropout levels, i.e., percentages, for the various relevant student categories, e.g., gender, quizzes, work experience. These trees can be used to identify a set of interventions that maximizes the chances of transforming a student at risk into the mainstream student body. The primary purpose of this presentation is to highlight how knowledge discovery can be used to design specific intervention strategies with the goal of improving both student retention and overall learning outcomes throughout the management education community of practice.

Keywords:

Knowledge discovery, students at risk, intervention strategies, machine learning, student success.