Students Real Data Features Analyzing with Supervised Learning Algorithms to Predict Efficiency
Hussein Neamah Zamzeer Al-Jizani
Dr. Ayla Kayabaş
Keywords: Prediction, Machine Learning, Education.
Abstract
Higher education institutions strive to predict the results of their students, and this endeavor represents a significant area of research. The ability to predict student achievement can provide educators with several benefits, including the ability to prevent students from dropping out before final examinations, to identify individuals who require further assistance, and to improve an institution's rating and status. Also, it is highly crucial to investigate the qualities shared by institutions that have produced successful graduates within their student body. Consideration is given to every requirement that must be met before the learner can be considered successful. In the field of educational data mining, machine learning techniques are used with the goal of developing a model that can uncover hidden significant patterns and extract usable information from educational environments. The most important features that have traditionally been associated with students are the most important underlying elements that may be used to represent the training dataset for supervised machine learning algorithms. We evaluate the efficacy of a number of supervised machine learning algorithms and propose the ones that perform the best when applied to the data collected from the students. The process might be made more effective by utilizing a model recommendation system to make suggestions for the most suitable educational institutions for new students.
