The paper "Artificial Intelligence Bringing Improvements to Adaptive Learning in Education: A Case Study" by Claudio Giovanni Demartini, Luciano Sciascia, Andrea Bosso, and Federico Manuri explores the integration of learning analytics and artificial intelligence (AI) in educational settings, particularly in primary and secondary schools. Despite the promising outcomes in higher education, the widespread adoption of learning analytics remains limited, with schools showing significant reluctance. The authors aim to address this challenge by developing a user-friendly AI-based dashboard for learning analytics, which can help identify vulnerable or exceptional learners and enable educational authorities to take appropriate actions. The dashboard is designed to support teachers and decision-makers in enhancing educational processes and organizational structures. The paper outlines the Data2Learn@Edu project, which involves multiple partners and focuses on creating statistical models based on historical data about students and teachers. These models aim to adapt to students' profiles and recommend organizational adjustments. The project uses a closed-loop control model to create an adaptive teaching and learning framework, integrating data mining and machine learning techniques. The sensor component analyzes student data, grouping them into clusters, and comparing these profiles with expected profiles to identify areas for improvement. The regulator then devises corrective actions based on the differences between the offered and expected profiles. The case study presented is from the Innovation Management and Product Development course at Politecnico di Torino, where the active learning methodology is applied. This approach combines traditional and constructivist methods, with a focus on project-based learning and collaborative work. The course structure is designed to mirror the project life cycle, with students actively involved in problem-solving and project development. The assessment process includes project work, tests, and self-assessment mechanisms, ensuring a comprehensive evaluation of student performance. Overall, the paper highlights the potential of AI and learning analytics to revolutionize education by providing valuable insights for decision-making, enhancing student engagement, and improving educational outcomes. However, it also emphasizes the importance of ethical considerations, data privacy, and transparency in the use of these technologies.The paper "Artificial Intelligence Bringing Improvements to Adaptive Learning in Education: A Case Study" by Claudio Giovanni Demartini, Luciano Sciascia, Andrea Bosso, and Federico Manuri explores the integration of learning analytics and artificial intelligence (AI) in educational settings, particularly in primary and secondary schools. Despite the promising outcomes in higher education, the widespread adoption of learning analytics remains limited, with schools showing significant reluctance. The authors aim to address this challenge by developing a user-friendly AI-based dashboard for learning analytics, which can help identify vulnerable or exceptional learners and enable educational authorities to take appropriate actions. The dashboard is designed to support teachers and decision-makers in enhancing educational processes and organizational structures. The paper outlines the Data2Learn@Edu project, which involves multiple partners and focuses on creating statistical models based on historical data about students and teachers. These models aim to adapt to students' profiles and recommend organizational adjustments. The project uses a closed-loop control model to create an adaptive teaching and learning framework, integrating data mining and machine learning techniques. The sensor component analyzes student data, grouping them into clusters, and comparing these profiles with expected profiles to identify areas for improvement. The regulator then devises corrective actions based on the differences between the offered and expected profiles. The case study presented is from the Innovation Management and Product Development course at Politecnico di Torino, where the active learning methodology is applied. This approach combines traditional and constructivist methods, with a focus on project-based learning and collaborative work. The course structure is designed to mirror the project life cycle, with students actively involved in problem-solving and project development. The assessment process includes project work, tests, and self-assessment mechanisms, ensuring a comprehensive evaluation of student performance. Overall, the paper highlights the potential of AI and learning analytics to revolutionize education by providing valuable insights for decision-making, enhancing student engagement, and improving educational outcomes. However, it also emphasizes the importance of ethical considerations, data privacy, and transparency in the use of these technologies.