Impacts of Students Academic Performance Trajectories on Final Academic Success

TL;DR

This paper uses a Hidden Markov Model to classify student academic trajectories and finds that both improving and worsening performance patterns can be associated with higher graduation rates, challenging conventional assumptions.

Contribution

The study introduces a novel application of HMM to represent academic performance trajectories and reveals complex relationships between these trajectories and final academic success.

Findings

Higher academic performance levels correlate with lower halt rates.

Both improving and worsening trajectories can lead to higher graduation rates.

HMM provides an intuitive classification of student academic paths.

Abstract

Many studies in the field of education analytics have identified student grade point averages (GPA) as an important indicator and predictor of students' final academic outcomes (graduate or halt). And while semester-to-semester fluctuations in GPA are considered normal, significant changes in academic performance may warrant more thorough investigation and consideration, particularly with regards to final academic outcomes. However, such an approach is challenging due to the difficulties of representing complex academic trajectories over an academic career. In this study, we apply a Hidden Markov Model (HMM) to provide a standard and intuitive classification over students' academic-performance levels, which leads to a compact representation of academic-performance trajectories. Next, we explore the relationship between different academic-performance trajectories and their correspondence to final academic success. Based on student transcript data from University of Central Florida, our proposed HMM is trained using sequences of students' course grades for each semester. Through the HMM, our analysis follows the expected finding that higher academic performance levels correlate with lower halt rates. However, in this paper, we identify that there exist many scenarios in which both improving or worsening academic-performance trajectories actually correlate to higher graduation rates. This counter-intuitive finding is made possible through the proposed and developed HMM model.