Date of Award

12-15-2025

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Computer Science

First Advisor

Xiaowei Xu

Abstract

Higher education institutions strive to support students in achieving their academic goals through targeted interventions and data-driven strategies. This study analyzed 19 variables, spanning student demographics, enrollment patterns, and institutional interventions, to identify predictors of students completing all enrolled courses in a semester. Using random forest, logistic regression, and bootstrap forest models, we assessed variable importance and derived causal estimates to determine their impact. Results from causal analysis indicate positive effects from session type, term load, referrals, kudos, flags, and scholarships, while negative impacts were associated with location, course delivery method, enrollment status, advisor contact, and registration interval. These findings offer actionable insights for institutions seeking to enhance student success through evidence-based interventions. Additionally, the study explored the use of generative AI models, via retrieval-augmented generation (RAG) and fine-tuning, to compare their predictive and causal reasoning capabilities against DoWhy-based causal inference. The results demonstrate the potential of AI-driven approaches to complement traditional statistical methods in identifying and optimizing strategies for student success.

Download

Share

COinS