Analysis of Student Risk Factor on Online Courses using Radom Forest Algorithm in Machine Learning
S. Anna Lakshmi
S. Gokul raja
D. Pushparaj
S. Sakthivel
T. Sathish kumar
Keywords: Machine Learning, Risk Factor
Abstract
The study's goal was to use the Random Forest method in Machine Learning to analyse student risk variables in online courses. The study employed a dataset of online course students to collect information on their demographics, academic achievement, and online activities. After that, the Random Forest algorithm was used to determine the most relevant risk factors influencing student achievement in online courses.
The Random Forest algorithm was found to be successful in identifying the most relevant risk factors influencing student achievement in online courses. The algorithm discovered numerous crucial characteristics in determining student performance in online courses, including student involvement, course difficulty, and time management abilities. Students who participated in online forums and received frequent feedback from professors were also shown to be more likely to succeed in online courses, according to the study.
Overall, the results indicate that the Random Forest algorithm can be a useful tool for identifying the most critical risk variables influencing student achievement in online courses. The study gives useful insights into how online courses can be designed to assist student success and emphasises the necessity of encouraging student engagement and delivering regular feedback in online learning environments.
