Course recommendation systems (CRS) are essential tools that help university students navigate their academic journey and select appropriate courses. Most of the existing models function as black boxes, offering little transparency in their recommendations. This lack of explainability reduces students' trust and willingness to adopt these systems, as they often want to understand the reasoning behind course suggestions. To address this issue, we introduce a knowledge graph-enhanced explainable course recommendation framework to provide personalized course recommendations to students in the upcoming semester. Our model, GGCR, integrates multiple techniques, including feature (keywords) extraction from course descriptions, graph attention networks (GAT) to build high-quality embeddings, and gated recurrent units (GRU) to capture session-based and sequential patterns over multiple semesters. We also explore the explainability capabilities of the best-performing models. We utilize course embeddings to offer course-similarity-based explanations. In addition, using the attention weights of the GAT module, our approach provides more detailed path reasoning-based explanations for each recommendation. In our experiments, conducted on real-world data, the proposed GGCR model not only exceeds existing state-of-the-art models in performance but also enhances explainability. This highlights that explainability does not have to come at the cost of accuracy. Furthermore, we assess the quality of different types of explanations using the Fidelity measure, large language models (LLMs), and human experts to ensure that our framework provides meaningful and interpretable recommendations.

Higher educational institutions constantly look for ways to meet students' needs and support them through graduation. However, even though institutions provide degree program curriculums and prerequisite courses to guide students, these often fail to capture some of the underlying skills and knowledge imparted by courses that may be necessary for a student.

An enduring issue in higher education is student retention and timely graduation. Early-warning and degree planning systems have been identified as a key approach to tackle this problem. Accurately predicting a student's performance can help recommend degree pathways for students and identify students at-risk of dropping from their program of study. Various approaches have been developed for predicting students' next-term grades. Recently, course-specific approaches based on linear regression and matrix factorization have been proposed. To predict a student's grade, course-specific approaches utilize the student's grades from courses taken prior to that course. However, there are a lot of factors other than student's historical grades that influence his/her performance, such as the difficulty of the courses, the quality and pedagogy of the instructor, the academic level of the students when taking the courses and so on. In this paper, we propose a course-specific regression model enriched with features about students, courses and instructors. Our proposed models were evaluated on datasets from two large public universities for academic programs with varying flexibility. The experimental results showed that incorporating content features can boost the performance of the course-specific model. For some degree programs with high flexibility, our experiments showed that predicting the grades with informative content features demonstrated better prediction accuracy.