Enhancing Academic Advisement with Case-Based Reasoning
Author: Tanat Tonguthaisri
arXiv: 2611.08572 [cs.AI]
Submitted: 5 November 2026
Comments: 2026 proofread digital edition of the August 2003 Master of Engineering thesis, RMIT University
Subjects: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
ACM Classes: I.2.1; K.3.1
DOI: 10.48550/arXiv.2611.08572
Abstract
This research examines the application of Case-Based Reasoning (CBR) to academic advising. Academic advisement is widely recognized as an important function of higher education; nevertheless, institutions around the world—including colleges and universities—continue to seek improvements in the advisement services they provide. Over the past decade, CBR expert systems have made significant contributions across many domains by applying CBR methodology to a range of human problem-solving tasks. Until now, however, expert advisement systems have not been successfully applied to academic advisement—a domain that appears especially well suited to this technology.
Academic advising is both important and time-consuming, and effective, efficient advising requires a variety of tools and techniques. This thesis describes the design, development, and validation of a prototype case-based academic advisement recommender system. The system is intended to supplement conventional advising processes and, once its full potential is realized, could eventually evolve to replace human academic advisors.
Context and Significance
The work is presented as a 2026 proofread digital edition of an August 2003 Master of Engineering thesis completed at RMIT University. Although the original research dates to the early 2000s, its central question—how to make academic advising more effective and scalable through intelligent systems—remains highly relevant in 2026. Contemporary institutions face growing student populations, increasingly complex program requirements, and rising expectations for personalized guidance, all of which heighten interest in AI-assisted advising.
Case-based reasoning offers a distinctive approach in this landscape: rather than relying solely on rule-based logic, a CBR system retrieves and adapts solutions from prior advising cases. This makes it naturally aligned with the experiential, precedent-driven nature of academic guidance, where past student scenarios often inform recommendations for new ones. The prototype described in this thesis thus anticipates today's broader movement toward recommender systems and decision-support tools in higher education.
Key Contributions
- Domain application: Applies CBR methodology to academic advisement, a domain previously underserved by expert advisement systems.
- System design and development: Details the architecture and implementation of a prototype case-based academic advisement recommender system.
- Validation: Reports on the validation of the prototype as a supplement to conventional advising processes.
- Forward-looking scope: Considers the system's potential to evolve beyond supplementation toward replacement of human advisors as its capabilities mature.
Citation
Tonguthaisri, T. (2026). Enhancing Academic Advisement with Case-Based Reasoning.
arXiv:2611.08572 [cs.AI]. https://doi.org/10.48550/arXiv.2611.08572
via ArXiv AI