a review of decision tree algorithms and their applications in academic guidance: a systematic literature review

This systematic literature review (slr),conducted according to the prisma framework, provides acomprehensive analysis of research conducted between 2020and 2025 on the application of decision tree algorithms inacademic guidance. following a rigorous search that identified500 articles, a multi-stage screening process led to the inclusionof 78 high quality studies. this review synthesizes thetheoretical foundations, advancements, applications,challenges, and future directions of these algorithms. findingsindicate that decision trees, due to their high interpretability,transparency, and hierarchical structure, serve as effectivetools in educational decision-making. they are particularlyprominent in student performance prediction and courserecommendation systems, where they have demonstrated highaccuracy (82–95%) and contributed to a 15% or greaterincrease in course completion rates. despite their technicalsuccess, emerging challenges include ethical concerns such asalgorithmic bias, data privacy, and scalability. currentresearch trends are shifting toward hybrid models, explainableai (xai), and real-time, scalable systems. the reviewconcludes that decision trees have the potential to revolutionizepersonalized education. to fully realize this potential, futureresearch must simultaneously focus on three pillars: (1)enhancing technical performance through interpretable andhybrid models, (2) ensuring ethical principles such as fairness,transparency, and privacy, and (3) improving practicalapplicability via real-time and scalable systems. only throughthis comprehensive approach can academic guidance systemsevolve into intelligent, equitable, and trustworthy tools thatgenuinely support the success of all students.