Artificial Intelligence Decision Tree Model of Construction Students' Four-Year Outcome

10 pages•Published: June 2, 2026

Tulio Sulbaran, Jared Burgoon, Olugbenro Ogunrinde and Rachel Mosier

Abstract

The construction industry faces a critical shortage of skilled professionals, making student persistence and on-time graduation within construction management programs a vital concern. The objective of this research was to identify and map critical student characteristics associated with four-year graduation within a university-level construction workforce pathway program. The study employed a quantitative research methodology to analyze fourteen years of institutional research data from n=613 undergraduate student records. Specifically, a transparent and interpretable Artificial Intelligence (AI) Decision Tree model was utilized to analyze this extensive dataset and classify it into the likelihood of graduating, or not, within four years based on factors influencing the students. The results show a significant disparity in students graduating within four years based on certain student characteristics. Similarly, there are other characteristics that make the students less likely to graduate. This second finding, in the authors’ opinion, is the most important as it allows universities to use their limited resources to assist these students in increasing their graduation rate to join the construction industry with their degrees. The intellectual merit of this research lies in its enhanced understanding of students’ characteristics who do not graduate within four years. This study's broader impact is that it provides data-driven, actionable insights for universities to implement targeted interventions, potentially mitigating the critical shortage of skilled construction professionals.

Keyphrases: artificial intelligence, construction, graduation, intervention, persistence, students

In: Wesley Collins, Anthony Perrenoud and John Posillico (editors). Proceedings of Associated Schools of Construction 62nd Annual International Conference, vol 7, pages 41-50.

Links:	https://easychair.org/publications/paper/GkdM
	https://doi.org/10.29007/x8dp

BibTeX entry

@inproceedings{ASC2026:Artificial_Intelligence_Decision_Tree,
  author    = {Tulio Sulbaran and Jared Burgoon and Olugbenro Ogunrinde and Rachel Mosier},
  title     = {Artificial Intelligence Decision Tree Model of Construction Students' Four-Year Outcome},
  booktitle = {Proceedings of Associated Schools of Construction 62nd Annual International Conference},
  editor    = {Wesley Collins and Anthony Perrenoud and John Posillico},
  series    = {EPiC Series in Built Environment},
  volume    = {7},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2632-881X},
  url       = {/publications/paper/GkdM},
  doi       = {10.29007/x8dp},
  pages     = {41-50},
  year      = {2026}}

Download PDF Open PDF in browser