A Prediction Model for Student Academic Performance Using Machine Learning-Based Analytics

Abstract

The adoption of digitization in the education sector has led to transformational changes. The academic sector has become more digital, more extensive, and more comprehensive but more complex as well. The topical advancements include the rise of technology-driven learning, the use of digital learning platforms, management systems, and technologies by students; the implementation of artificial intelligence and machine learning approaches for improvising student learning. In recent times, the solicitation of machine learning into academics has led to an upsurge in the education sector embroidering the growth of novel arenas such as Academic Data Mining (ADM) or Education Data Mining (EDM). ADM, based on machine learning techniques, helps in the prediction of students’ academic performance and is the subject of concern to many academic institutions for the classification of its students according to their learning capabilities. Moreover, the enormous amount of data about student academics can be handled, pre-processed, analyzed, and transformed into meaningful results and interesting patterns. The resulting patterns help in analyzing the academic performance of students and further lead to the identification of students who require special counseling. This paper proposes a model that predicts the performance of students based on academic details that helps in the classification of different learners.