Data integrity analysis and performance in online courses using machine learning methods
Mobile learning, Data mining, Machine learning, Open data.
This work aims a research that focuses on analyzing data integrity and performance in online courses, using machine learning methods. My proposal is to develop a tool capable of predicting the number of students who complete the course and identify possible cases of dropout or withdrawal. For this, it uses supervised machine learning algorithms, such as support vector machines (SVM) and artificial neural networks (ANNs), which enable a detailed and predictive analysis of the data. The approach I adopted for my research was qualitative bibliographic, exploring data from online courses and using data analysis techniques. Through these machine learning methods, i was able to identify patterns and trends in the data, allowing for a deeper understanding of the integrity of the records and student performance. This provides a solid basis for strategic decision-making by managers for staff training. The main goal of this analysis is to improve the efficiency and quality of online courses. With the tool I am proposing, it is possible to anticipate course completion results, identify factors that influence student dropout and implement strategies to increase the completion rate. By having a more accurate view of the students’ profile and the challenges they face, we can take proactive measures to improve course delivery and provide a more satisfying learning experience