AI-Driven Personalized Learning Systems for Enhancing Educational Outcomes in Data-Driven Environments

Recent developments in artificial intelligence (AI) have excited an interest in applying it in educational systems to present personalized learning experiences. The goal of this work was to assess the effectiveness of AI-enabled personalized learning systems in improving education quality through simulation-based data analysis. The study used a quantitative experimental design for the study, and Python in Google Colab was employed for the simulation of student interactions with AI systems, and the results were analysed using regression and classification models. The results explained the variance of performance outcome around $40 \%$ (R -squared: 0.398) and found a strong association between engagement and performance scores. It shows that such systems can successfully increase outcomes for learning if they focus on the engagement of the learner. Future research is advised to include additional dynamic learning variables. The implications for such research are practical; firstly, they suggest that there is the potential use of AI to make adaptive learning environments that increase learning engagement and performance. Nevertheless, the use of simulated data is a limitation and calls for trials of these data in real educational settings to confirm these results.