Abstract
This study examined the effect of Artificial Intelligence (AI)-enabled adaptive learning systems and intelligent tutoring technologies on personalized learning outcomes among undergraduate students in Nigerian public universities. The study was motivated by persistent gaps in higher education delivery, particularly overcrowded classrooms, limited lecturer-student interaction, inadequate instructional support, unequal access to quality learning resources, and weak digital infrastructure. These challenges have continued to limit students’ engagement, learning autonomy, and academic performance, thereby creating the need for technology-driven instructional models that can support individualized learning. The objective of the study was to determine the extent to which AI-enabled adaptive learning systems influence personalization, student engagement, and academic performance among undergraduates in selected Nigerian public universities. The study was anchored on Constructivist Learning Theory and the Technological Pedagogical Content Knowledge (TPACK) framework. A quantitative survey research design was adopted. The population comprised undergraduate students in selected federal universities in Nigeria, while a sample size of 600 respondents was used for the study. Respondents were selected through a multi-stage sampling technique, involving the purposive selection of universities and the random selection of undergraduate participants. Data were collected using a structured questionnaire and analyzed using descriptive statistics, reliability analysis, correlation, and multiple regression analysis. The findings revealed that AI-enabled adaptive learning significantly improves personalized learning experiences, student engagement, and academic performance. Cronbach’s alpha values ranged from 0.825 to 0.917, indicating strong internal consistency of the research instrument. Academic performance recorded the highest mean score (M = 3.89), followed by engagement (M = 3.83) and personalization (M = 3.76), suggesting positive student perceptions of AI-supported learning. Regression results further showed that AI access, personalization, and engagement jointly explained a substantial proportion of variation in academic performance (R² ≈ 0.42–0.55). However, infrastructural constraints negatively moderated the effectiveness of AI-enabled learning. The study concludes that AI-driven personalized learning can enhance academic outcomes when supported by adequate infrastructure, institutional readiness, and lecturer capacity. It recommends increased investment in digital infrastructure, faculty training, policy support, and ethical AI integration in Nigerian higher education.