Graphs Regularized Robust Matrix Factorization and Its Application on Student Grade Prediction

Abstract

Student grade prediction (SGP) is an important educational problem for designing personalized strategies of teaching and learning. Many studies adopt the technique of matrix factorization (MF). However, their methods often focus on the grade records regardless of the side information, such as backgrounds and relationships. To this end, in this paper, we propose a new MF method, called graph regularized robust matrix factorization (GRMF), based on the recent robust MF version. GRMF integrates two side graphs built on the side data of students and courses into the objective of robust low-rank MF. As a result, the learned features of students and courses can grasp more priors from educational situations to achieve higher grade prediction results. The resulting objective problem can be effectively optimized by the Majorization Minimization (MM) algorithm. In addition, GRMF not only can yield the specific features for the education domain but can also deal with the case of missing, noisy, and corruptive data. To verify our method, we test GRMF on two public data sets for rating prediction and image recovery. Finally, we apply GRMF to educational data from our university, which is composed of 1325 students and 832 courses. The extensive experimental results manifestly show that GRMF is robust to various data problem and achieves more effective features in comparison with other methods. Moreover, GRMF also delivers higher prediction accuracy than other methods on our educational data set. This technique can facilitate personalized teaching and learning in higher education.

Integrated Sparse Coding With Graph Learning for Robust Data Representation

“…An order-graph regularized dictionary learning was proposed for 3D ultrasound image reconstruction, where LogSC could be used to further keep the low-rank structure of the needles in 2D slices [55]. Since similar students have similar grades and similar course have similar grades, the student grade matrix has a low-rank structure ignored by the graph robust matrix factorization [56]. LogSC could be developed to learn the latent features for students and courses by exploiting the low-rank structure, meanwhile considering the side information from demography.…”

Multiclass Prediction Model for Student Grade Prediction Using Machine Learning

“…However, the most common factors are relying on socioeconomic background, demographics [3], and learning activities [4] compared to final student grades in the final examination [5]. For this reason, we observe that predicting student grades can be one of the solutions that are applicable to improve student academic performance [6].…”

Undergraduate Grade Prediction in Chinese Higher Education Using Convolutional Neural Networks

“…As a basic problem in both LA and EDM, student grade prediction provides objective evidence to the stakeholders: students choose self-benefited course plans; teachers make good teaching plans; managers launch suitable curriculum plans [18]. In the past decade, many studies have been developed using various machine learning techniques and could be mainly divided into: matrix factorization-based methods [23] [16] [22], similarity-based methods [5] [10], and mapping-based methods [11] [9].…”

“…al. proposed a graph regularized robust matrix factorization to take both student's side-information and course's side-information into account [23]. Zhu et.…”