A Novel Metaheuristic Approach to Optimization of Neuro-Fuzzy System for Students' Performance Prediction

Abstract

Today, technology is aggressively adopted by educational institutes to maximize output of existing resources, to benefit both students and the teachers. The use of technology-based learning makes it possible to collect enormous amount of data pertaining to student and teacher performance. This data is then used for extracting meaningful information that deems useful for administration in making efficient decisions. For this purpose, literature shows significant advantages of data mining and machine learning techniques with regards to educational data mining [1,2,3]. Utilizing behavioral and performance data of students and teachers, researchers have applied these methods to discover knowledge in hidden patterns, to assess the effectiveness of courses, teaching methodologies, curriculum, and overall education system [4]. More specifically, the educational data mining is now being used to predict students' performances in order to identify the vulnerable ones at risk of failing the upcoming examinations so that more focus could be drawn on them to solve any difficulties [5,6].

A Systematic Literature Review of Student’ Performance Prediction Using Machine Learning Techniques

“…Hussain et al [76] applied a machine-learning-based methodology for the expected performance prediction of students. They collected the curricular data and non-curricular data from university daily activities.…”