Integration of Machine Learning Algorithms for E-Learning System Course Recommendation Based on Data Science
K. K. Ramachandran, Sakshi Sandeep Phatak, Shaik Vaseem Akram, Vijay Kumar Patidar, Adusupalle Muni Raju, R. Ponnusamy · 2023
A big database is mined for hidden predictive information in a process known as data mining. This information can then be used for a variety of commercial purposes, including bioinformatics and e-commerce. There are three different data mining algorithms: association rules, classification, and clustering. The behaviour of students who are interested in a specific collection of courses can be recognized with the help of the course recommender system. For a particular collection of information, we get information on course enrolment. We use learning management systems like Moodle for gathering this data. Following data collection, several combinations of data mining algorithms are used, such as classification and association rule algorithms, clustering and association rule algorithms, mining in classified and clustered data, integrating clustering and classification algorithms in association rule algorithms, or just the cluster analysis algorithm. As various machine learning algorithms, we employ ADTree classification, Simple K-means, and Apriori Association Rules in this research. So, in order to determine the optimum algorithmic combination for proposing courses to students using online learning, we provide five distinct ways. We compare the outcomes of this combined strategy with those of using simply the association rule algorithm, and we propose the optimum algorithmic combination for recommending courses in online learning based on our simulation.