The field of educational research is witnessing a significant shift towards leveraging artificial intelligence (AI) and machine learning (ML) to improve student outcomes and inform educational policies. Recent studies have demonstrated the potential of explainable AI techniques in predicting mathematics achievement and identifying key predictors across different countries. Additionally, there is a growing focus on developing innovative solutions to support struggling students, including the use of proficiency taxonomies and graph-level representation learning approaches. These advancements have the potential to enhance personalized learning strategies, alleviate performance gaps, and provide educators with rich insights into student learning journeys. Noteworthy papers include: Explainable AI for Predicting and Understanding Mathematics Achievement, which applied XAI techniques to PISA 2018 data to predict math achievement and identify key predictors. Detecting Struggling Student Programmers using Proficiency Taxonomies, which developed a taxonomy of proficiencies to categorize student programming skills and predict struggling students. MAB Optimizer for Estimating Math Question Difficulty, which introduced a reinforcement learning-based framework to estimate question difficulty without requiring linguistic features or expert labels.