Title: A Markov Decision Processes Modeling for Curricular Analytics
Abstract:
The curricula structure and the complexity of their prerequisite dependencies proved to be essential factors that impact student progression and ultimately graduation rates. However, there are no available tools in the literature that quantify the relationship between the complexity of curricula structure and graduation rates. This paper introduces a new method that captures this relationship using Markov Decision Processes (MDP). The non-deterministic nature of students’ progresses along with their evolving states at each semester make MDP a suitable framework for this work. The novelty of the proposed model is mainly characterized by its closed-form solution approach that can be utilized to perform “what-if” analysis upon modifying curricula structure. The results confirm the converse relationship between the complexity of curricula structure and graduation rates. This is validated using a Monte Carlo simulation method. The results also provide useful insights to purse more complex implementations for prospective future work.
Speaker:
Husain Al Yusuf
PhD Student
University of Arizona
Date/Time: August 6, 2021, 2pm PDT, 5pm EDT
Video: https://www.youtube.com/watch?v=H5twoaL4pmA&ab_channel=HigherEducationAnalytics