Data analytics of students' profiles and activities in a full online learning context

The use of a Learning Management System (LMS) in e-learning makes it easier for teachers to track and record student learning behavior. The right analytics of e-learning students can help teachers understand the student context and what learning experiences are most suitable for e-learning students to improve learning outcomes. However, e-learning teachers often experience difficulties in analyzing student data due to a large number of students who must be analyzed and limited data. To support research in this area, we conducted a descriptive analysis of a dataset containing student data from the Open and Distance Learning (ODL) that organizes e-learning. The dataset contains data on student demographic profiles and student activity or behavior during e-learning which is recorded in the LMS system at the Open University of Indonesia. In this initial study, the dataset contained information from 120 classes in 18 subjects with 4, 741 students from 33 study programs with many logs on LMS 1, 641, 234 entries. This article presents an analytical description of the characteristics of students participating in e-learning using Exploratory data analytics (EDA) and machine learning approaches as the basis for predictive and prescriptive analytics of student learning outcomes based on a combination of demographic profile data and learning behavior. This study helps education practitioners in the first step of analytics data as the basis for developing e-Learning instructional designs that support the success of fully online students.