A Semi-Supervised Regression Algorithm for Grade Prediction of Students in Distance Learning Courses

2019 ◽  
Vol 28 (04) ◽  
pp. 1940001 ◽  
Author(s):  
Georgios Kostopoulos ◽  
Sotiris Kotsiantis ◽  
Nikos Fazakis ◽  
Giannis Koutsonikos ◽  
Christos Pierrakeas
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Undergraduate Students ◽  
Educational Data Mining ◽  
Predictive Performance ◽  
Educational Process ◽  
Training Set ◽  
Final Grade ◽  
Future Outcomes ◽  
Educational Field

Applying data mining methods in the educational field has gained a lot of attention among researchers in recent years. Educational Data Mining has turned into an effective tool for uncovering hidden relationships in educational data and predicting students’ learning outcomes. Several supervised methods have been successfully applied with the purpose of identifying students at risk of failing or of predicting their academic performance. Recently, the implementation of Semi-Supervised Learning (SSL) methods in the educational process indicated their superiority over the supervised ones. SSL is an emerging subfield of machine learning seeking to effectively exploit a small pool of labeled examples together with a large pool of unlabeled ones. On this basis, a small number of students’ data from previous years may be used as the training set of a learning model to predict future outcomes of current students. A number of rewarding studies deal with the implementation of classification methods in the educational field in contrast to regression, which is deemed to be a slightly touched task. In this paper, a novel semi-supervised regression (SSR) algorithm is presented for predicting the final grade of undergraduate students in a distance online course. To the best of our knowledge there is no study dealing with the implementation of SSR methods in the educational field. A plethora of attributes related to students’ characteristics, academic performance and interaction within the course online platform form the training set, while several experiments were carried out confirming the superiority of the proposed algorithm over familiar regression methods. The experiment results show that the predictive performance of the proposed algorithm is increasing significantly over time, achieving a MAE value of less than 1.2358 before the middle of the academic year, which provides the advantage of early warnings and interventions.

scholarly journals Educational Data Mining, Student Academic Performance Prediction, Prediction Methods, Algorithms and Tools: An Overview of Reviews

2021 ◽  
Author(s):  
Chaka Chaka
Keyword(s):  
Higher Education ◽  
Data Mining ◽  
Academic Performance ◽  
Educational Data Mining ◽  
Overview Of Reviews ◽  
Student Demographics ◽  
Student Academic Performance ◽  
Online Databases ◽  
Subject Areas ◽  
Input Variables

This overview study set out to compare and synthesise the findings of review studies conducted on predicting student academic performance (SAP) in higher education using educational data mining (EDM) methods, EDM algorithms and EDM tools from 2013 to June 2020. It conducted multiple searches for suitable and relevant peer-reviewed articles on two online search engines, on nine online databases, and on two online academic social networks. It, then, selected 26 eligible articles from 2,050 articles. Some of the findings of this overview study are worth mentioning. First, only 2 studies explicitly stated their precise sample sizes with maths and science as the two most mentioned subject areas. Second, 16 review studies had purposes related to either EDM techniques, EDM methods, EDM models, or EDM algorithms employed to predict SAP and student success in the higher education sector. Third, there are six commonly used typologies of input variables reported by 26 review studies, of which student demographics was the most commonly utilised variable for predicting SAP. Fourth and last, seven common EDM algorithms employed for predicting SAP were identified, of which Decision Tree emerged both as the most used algorithm and as the algorithm with the highest prediction accuracy rate for predicting SAP.

scholarly journals An Effectual Ga Based Association Rule Generation and Fuzzy Svm Classification Algorithm for Predicting Students Performance

2019 ◽  
Vol 8 (6) ◽  
pp. 2915-2920
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Association Rule ◽  
Educational Data Mining ◽  
Rule Generation ◽  
Academic Status ◽  
Student Records ◽  
Performance Simulation ◽  
Svm Classification ◽  
Student’S Performance

This investigation provides outcome of utilizing educational data mining [EDM] to design academic performance of students from real time and online dataset collected from colleges. Data mining is determined to examine non-academic and academic data; this model utilizes a classification approach termed as Fuzzy SVM classification with Genetic algorithm to attain effectual understanding of association rule in enrolment and to evaluate data quality for classification, which is identified as prediction task of performance and academic status based on low academic performance. This model attempts to predict student’s performance in grading system. Academic and student records attained from process were considered to train models estimated using cross-validation and formerly records from complete academic performance. Simulation was performed in MATLAB environment and show that academic status prediction is enhanced while hybrid dataset are added. The accuracy was compared with the existing models and shows better trade off than those methods.

scholarly journals Effect of Academic Interest and Emotional Happiness on Academic Performance in Learning Environment.

2020 ◽  
Vol 9 (1) ◽  
pp. 2486-2489
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Clustering Algorithm ◽  
Reference Model ◽  
Educational Data Mining ◽  
Positive Association ◽  
Academic Interest ◽  
Education Data ◽  
Learning Techniques ◽  
And Performance

According to Bloom's Taxonomy, the motto of education is to groom the students' as a better personality in knowledge, skill set and emotions under the supervision of academicians. Development of information technology paves the way to analyse the data from the educational environment and make decisions which help to be in track to achieve the motto. i.e. Educational Data mining. Education Data mining is one of the research domains of data mining which convert the data from the educational sector as insights for decision making. This paper is to analyse the effect of student's academic interest on emotional happiness and academic performance by applying supervised and unsupervised learning techniques. Students' Emotional Happiness and students' academic performance is evaluated by the Oxford Happiness Inventory and criterion reference model. Academic interest is received as yes or no responses from the students. Naive Bayes classification algorithm and K Means clustering algorithm is applied to categorise the student participants based on their happiness scale, academic interest and academic performance. The association between academic interest and performance is determined using predictive and descriptive mining. By this research, it is witnessed the positive association between academic interest, happiness and performance. The insights of this investigation will allow the teachers' to understand the students in a better way and do the needful to enhance academic efficiency.

Sign in / Sign up

Export Citation Format

Share Document