Rapid advances in technology are transforming education. The emergence of a variety of e-learning platforms and the growing ability to personalize learning have changed the way students interact with educational content. Today, students can access materials that are not only easily accessible, but also tailored to their unique learning needs and preferences.

Collecting and analyzing student performance data has become an integral part of this personalized approach. Using data, educators can create customized learning paths that match each student’s abilities and goals. Moreover, enhancing the learning environment with this data ensures that students receive the most effective and relevant educational experience possible.

While manual data recording and processing can achieve these results, it is a labor-intensive and time-consuming process that is prone to human error, making it an ineffective approach in the long run. This highlights the critical importance of automating data collection and processing, which not only improves accuracy but also significantly increases the efficiency of educational systems. Among the most promising advances in this area are deep machine learning techniques, which offer vast research opportunities, especially in the field of education. The application of deep learning in this context can significantly improve the efficiency of student learning. By effectively analyzing user data, deep learning algorithms can adapt and optimize the educational content provided to students, making accurate recommendations and predicting the most suitable individual learning paths. The main goal of this study is to use the capabilities of deep machine learning techniques to identify the most effective student registration tools available on the Moodle learning platform. Analyzing the data obtained by these tools, finding opportunities to predict learning success and preventing student dropout are effective tools for organizing the learning process for instructors, improving student learning outcomes and contributing to a more adaptive and responsive learning environment.

Keywords: Logging data, data processing, adaptive learning, student’s attributes.