Smart Pathfinder: An AI-Integrated Academic Advising Platform for Personalized Course Recommendation and Career Guidance

Modern higher education environments face significant challenges in student retention and academic progression due to the increasing complexity of specialized curricula. In the Philippine context, academic advising is traditionally a manual and reactive process, often leading to "choice paralysis" among students and delayed graduation. This study addresses these systemic inefficiencies by developing Smart Pathfinder, an AI-integrated platform designed to transition advising from a clerical task to a data-driven strategic intervention. The primary objective of this research was to engineer a proactive system capable of providing personalized course recommendations based on prerequisite logic, implementing real-time predictive risk analysis to identify at-risk students, and offering industry-aligned career guidance. The methodology followed a developmental research design integrated with an Agile Software Development Life Cycle, allowing for iterative refinement of the system’s core algorithms. The platform was built using a Python-based backend for machine learning logic and a MySQL database for secure student record management. System validation was conducted through rigorous functional testing and data accuracy verification across three core modules: Course Recommendation, Risk Analytics, and Career Mapping. Key results demonstrate that the system achieved 100% accuracy in prerequisite validation and successfully categorized students into high, moderate, and low-risk levels based on GPA fluctuations and historical performance trends. By visualizing academic health through institutional analytics dashboards, the system allows advisors to intervene as early as the fourth week of a semester. The study concludes that the integration of Artificial Intelligence into student support services significantly enhances institutional efficiency and reduces the administrative burden on faculty. Smart Pathfinder effectively bridges the gap between academic compliance and professional readiness, offering a scalable model for modernizing academic advising in Philippine Higher Education Institutions.

Academic Advising; Artificial Intelligence

1. Albreiki, B., Zaki, N., & Alashwal, H. (2021). A systematic review of early warning systems in higher education using predictive analytics and data mining. IEEE Access, 9, 121844–121860. https://doi.org/10.1109/ACCESS.2021.3108435 [Google Scholar] [Crossref]

2. Almulla, M. A. (2024). Integrating artificial intelligence into university academic advising: A systematic review of tools and institutional outcomes. Frontiers in Education, 9, Article 1341567. https://doi.org/10.3389/feduc.2024.1341567 [Google Scholar] [Crossref]

3. Bano, M., Zowghi, D., & Ikram, N. (2024). Web-based academic pathfinding algorithms and prerequisite rule enforcement: A systemic software life cycle review. Information and Software Technology, 168, Article 107124. https://doi.org/10.1016/j.infsof.2023.107124 [Google Scholar] [Crossref]

4. Bautista, J. M., & Santos, D. R. (2024). Automated prerequisite verification models in multi-track curriculum frameworks. Philippine Journal of Higher Education Innovation, 12(2), 88–104. [Google Scholar] [Crossref]

5. Brooke, J. (1996). SUS: A 'quick and dirty' usability scale. Usability Evaluation in Industry, 189–194. [Google Scholar] [Crossref]

6. Chen, T., & Wang, Y. (2023). Mitigating choice paralysis: Rule-based course recommendation filtering systems for technical undergraduate engineering. Computers & Education: Artificial Intelligence, 4, Article 100122. https://doi.org/10.1016/j.caeai.2023.100122 [Google Scholar] [Crossref]

7. Fahd, K., Miah, S. J., Ahmed, K., Venkatraman, S., & Siddiqui, S. (2022). Predicting student performance using deep neural networks and historical learning data profiles. Education and Information Technologies, 27(8), 11421–11443. https://doi.org/10.1007/s10639-022-11084-2 [Google Scholar] [Crossref]

8. Ghorbani, R., & Ghousi, R. (2024). Predictive risk analysis engines in academic institutions using multi-class classification models. Expert Systems with Applications, 238(Part C), Article 122180. https://doi.org/10.1016/j.eswa.2023.122180 [Google Scholar] [Crossref]

9. Kalaycioglu, O., Demir, E., & Toker, S. (2025). Aligning academic performance paths with real-world technological vocational taxonomies: A machine learning approach. Journal of Workplace Learning, 37(1), 15–34. https://doi.org/10.1108/JWL-05-2024-0091 [Google Scholar] [Crossref]

10. Kardan, A. A., Sadeghi, H., & Sani, M. F. (2023). Relational schema design and performance optimization of databases for institutional curriculum matrices. Computers & Education, 194, Article 104690. https://doi.org/10.1016/j.compedu.2022.104690 [Google Scholar] [Crossref]

11. Kitchenham, B., & Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering (Technical Report EBSE-2007-01). Keele University and University of Durham. [Google Scholar] [Crossref]

12. Liu, Y., Zhang, L., & Smith, J. R. (2022). Developing proactive data visualization dashboards for early risk discovery in higher education. International Journal of Educational Technology in Higher Education, 19(3), Article 42. https://doi.org/10.1186/s41239-022-00348-1 [Google Scholar] [Crossref]

13. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12(85), 2825–2830. [Google Scholar] [Crossref]

14. Sampson, J. P., Osborn, D. S., Kettunen, J., Hou, P. C., Miller, A. K., & Makela, J. P. (2024). Data-driven career competency mapping: Translating academic profile clusters into technological workforce pathways. The Career Development Quarterly, 72(1), 45–61. https://doi.org/10.1002/cdq.12345 [Google Scholar] [Crossref]

15. Viberg, O., Hatakka, M., Bälter, O., & Mavroudi, A. (2018). The current landscape of learning analytics in higher education: A review. Computers in Human Behavior, 89, 98–110. https://doi.org/10.1016/j.chb.2018.07.027 [Google Scholar] [Crossref]

16. Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2023). Data mining: Practical machine learning tools and techniques with Python implementations (5th ed.). Morgan Kaufmann. [Google Scholar] [Crossref]

• Smart Iot Device for Weather And Health
• Merlarchive: A Web-Based Academic Hub for UDM With AI-Powered Natural Language Processing
• Enhanced Social Network Security System: Integrating Biometric Authentication for Improved User Verification and Privacy Protection
• Smart Budget Allocation in Public Policy: A Data-Driven Approach for Equitable Resource Distribution
• Decision Support System for Faculty Selection, Promotion, and Reclassification Using Predictive Analytics