Authors : Peter N.Mulei; Salesio Kiura

Volume/Issue : Volume 8 - 2023, Issue 11 - November

Google Scholar : http://tinyurl.com/22yww4fz

Scribd : http://tinyurl.com/f7ftzxk3

DOI : https://doi.org/10.5281/zenodo.10427178

Abstract : The proliferation of e-learning platforms and blended learning environments has spurred a great deal of study on how to improve educational processes. The problem with the e-learning platforms, give the content as whole without considering the level of cognitivity of learners.One key factor is being able to forecast student performance with accuracy. Early in the learning process, it is useful to detect low-performing pupils based on a high forecast accuracy of their performance. But in order to accomplish these goals, a lot of student data needs to be examined and forecast using a variety of machine-learning models. Machine learning algorithms have shown to be a useful tool for focusing performances at different learning levels when used to forecast learners' actions based on their performance and background. For the purpose of enhancing learning outcomes, early student performance prediction is helpful. utilizing clever and flexible components to provide students with a personalized learning environment.Differentiating prediction levels by different machine-learning models may be the result of variations in socioeconomic conditions. Specialized scope classifiers are then merged into an ensemble to robustly forecast student achievement on learning objectives independently of the student's specific learning settings. Personalized Learning Environmentsimprove the educational process by offering specialized services that are based on the preferences of the learners.

Keywords : Machine Learning Algorithms, E-learning, Ensemble, Personalized, and Adaptive.