The Factor Affecting Student’s Performance of E-Learning Environment Using Machine Learning Algorithm

The Covid-19 pandemic is affecting many aspects of society, especially university educational programs worldwide. As a result, online learning is an effective strategy that is adopted by many educational institutions nowadays. However, not all training institutions have the necessary environment, assets, and ability to conduct effective online learning, particularly in poor nations with resource constraints. As a result, many institutions are struggling to build traditional courses or E-Learning in limited condition while still meeting students' demands. To overcome this limitation, we present a technique for assessing the impact of these elements on the e-learning system. Then, utilizing data from students who have participated in the program, this is an issue of explaining the significance and prioritizing construction investments for every component based on the K-means clustering algorithm. The purpose of this paper is to investigate the relationship between the students' responses to e-learning platforms and their performance in terms of various skill levels with the help of K-Means clustering algorithms. The clustering findings demonstrate that individuals with greater levels of involvement outperform those with intermediate or lower levels of engagement.