Predicting Students’ Performance Employing Educational Data Mining Techniques, Machine Learning, and Learning Analytics

Student success is important in colleges and universities since it is often used as a measure of the institution’s effectiveness. Identifying at-risk students early on and implementing preventative measures might have a major impact on their academic performance. In recent years, predictions made using machine learning techniques have become more common. Although there are many examples of successful utilization of data mining techniques in academic literature, these methods are frequently restricted to educators with expertise in computer science or, more specifically, artificial intelligence. Before implementing an effective data mining strategy, there are several decisions that must be made, such as defining student achievement, identifying important student characteristics, and selecting the most suitable machine learning approach for the particular issue. The objective of this investigation is to offer a complete set of instructions for educators interested in utilizing data mining techniques to predict student performance. To achieve this goal, we have analyzed the relevant literature and compiled the current state of the art into a methodical approach in which all the options and parameters are discussed at length and rationales have been given for their selection. By lowering the barrier to entry for data mining tools, this initiative will unleash their full potential for usage in the classroom.