No abstract

The last few years have witnessed an upsurge in the number of studies using Machine and Deep learning models to predict vital academic outcomes based on different kinds and sources of student-related data, with the goal of improving the learning process from all perspectives. This has led to the emergence of predictive modelling as a core practice in Learning Analytics and Educational Data Mining. The aim of this study is to review the most recent research body related to Predictive Analytics in Higher Education. Articles published during the last decade between 2012 and 2022 were systematically reviewed following PRISMA guidelines. We identified the outcomes frequently predicted in the literature as well as the learning features employed in the prediction and investigated their relationship. We also deeply analyzed the process of predictive modelling, including data collection sources and types, data preprocessing methods, Machine Learning models and their categorization, and key performance metrics. Lastly, we discussed the relevant gaps in the current literature and the future research directions in this area. This study is expected to serve as a comprehensive and up-to-date reference for interested researchers intended to quickly grasp the current progress in the Predictive Learning Analytics field. The review results can also inform educational stakeholders and decision-makers about future prospects and potential opportunities.

No abstract

No abstract

The CIM, PIM, and PSM models are the main levels of the MDA approach. Model transformation is an important step in the MDA process. Indeed, in MDA there are two elementary transformation kinds: CIM to PIM transformation and PIM to PSM transformation. However, most searches propose approaches transforming PIM to PSM, since there are multiple points in common between PIM and PSM. Nevertheless, transforming CIM to PIM is rarely addressed in research because these two levels are mainly different. However, there is not a synthesis work that makes it possible to carry out a model transformation from CIM to PIM towards PSM until obtaining the code. This synthesis methodology allows controlling models transformation from CIM to PIM to PSM, indeed, up to obtaining code according the MDA. This approach makes it possible to limit the intervention of computer scientists in the life cycle of software development. Indeed, this methodology allows modeling only CIM, the business process, and then obtains the source code through successive semi-automatic transformations.