Educational Data Mining Techniques for Student Performance Prediction: Method Review and Comparison Analysis

Abstract

Student performance prediction (SPP) aims to evaluate the grade that a student will reach before enrolling in a course or taking an exam. This prediction problem is a kernel task toward personalized education and has attracted increasing attention in the field of artificial intelligence and educational data mining (EDM). This paper provides a systematic review of the SPP study from the perspective of machine learning and data mining. This review partitions SPP into five stages, i.e., data collection, problem formalization, model, prediction, and application. To have an intuition on these involved methods, we conducted experiments on a data set from our institute and a public data set. Our educational dataset composed of 1,325 students, and 832 courses was collected from the information system, which represents a typical higher education in China. With the experimental results, discussions on current shortcomings and interesting future works are finally summarized from data collections to practices. This work provides developments and challenges in the study task of SPP and facilitates the progress of personalized education.

Self-paced graph memory for learner GPA prediction and it’s application in learner multiple evaluation

“…Student performance prediction is a core task in personalized education, and there have been many excellent related works in recent years. Zhang et al 18 summarized them as several methods, including traditional machine learning methods 19 , kernel methods 20 , collaborative filtering methods 21 , methods based on neural networks 22 , 23 , and so on. Among these methods, the neural network-based approach has attracted more extensive attention.…”

IntelliDaM: A Machine Learning-Based Framework for Enhancing the Performance of Decision-Making Processes. A Case Study for Educational Data Mining

“…Thus, an important direction in EDM is student performance prediction (SPP). SPP's target is to predict the grade of a student before attending a course or having an examination [23]. SPP problems require techniques from different domains: data mining, sociology, psychology, pedagogy, etc.…”

“…SPP problems require techniques from different domains: data mining, sociology, psychology, pedagogy, etc. [23]. There are some specific directions in the literature related to SPP: SPP of students at risk [24], [25], students' dropout prediction [26], [27], evaluation of students' performance [28], and remedial action plans [29].…”

“…There are some specific directions in the literature related to SPP: SPP of students at risk [24], [25], students' dropout prediction [26], [27], evaluation of students' performance [28], and remedial action plans [29]. According to the students' level or the educational field where SPP is needed, different features are considered to be "good predictors": grades, historical performance data [23], [30], students' demographic data [31], or students' behaviour [32] and engagement [33].…”

Influence Analysis of Education Policy on Migrant Children’s Education Integration Using Artificial Intelligence and Deep Learning

“…The experimental results showed that the designed model could explain students' performance through the generated curriculum relationship. Zhang et al (2021b) studied the impact of machine learning and data mining on students' performance, processed and analyzed the data in the dataset through five processes: data collection, problem formalization, model design, data prediction, and application effect, and finally summarized the discussion on the shortcomings of current teaching work. Zhang et al (2020) proposed a student knowledge diagnosis model to diagnose students' learning status by learning meta knowledge dictionary from students' answers.…”