Using educational data mining techniques to increase the prediction accuracy of student academic performance

2019 ◽  
Vol 120 (7/8) ◽  
pp. 451-467 ◽  
Author(s):  
Gomathy Ramaswami ◽  
Teo Susnjak ◽  
Anuradha Mathrani ◽  
James Lim ◽  
Pablo Garcia
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Random Forest ◽  
Predictive Accuracy ◽  
Process Mining ◽  
Educational Data Mining ◽  
Content Type ◽  
Student Activities ◽  
Data Mining Techniques ◽  
Student Academic Performance

Purpose This paper aims to evaluate educational data mining methods to increase the predictive accuracy of student academic performance for a university course setting. Student engagement data collected in real time and over self-paced activities assisted this investigation. Design/methodology/approach Classification data mining techniques have been adapted to predict students’ academic performance. Four algorithms, Naïve Bayes, Logistic Regression, k-Nearest Neighbour and Random Forest, were used to generate predictive models. Process mining features have also been integrated to determine their effectiveness in improving the accuracy of predictions. Findings The results show that when general features derived from student activities are combined with process mining features, there is some improvement in the accuracy of the predictions. Of the four algorithms, the study finds Random Forest to be more accurate than the other three algorithms in a statistically significant way. The validation of the best-known classifier model is then tested by predicting students’ final-year academic performance for the subsequent year. Research limitations/implications The present study was limited to datasets gathered over one semester and for one course. The outcomes would be more promising if the dataset comprised more courses. Moreover, the addition of demographic information could have provided further representations of students’ performance. Future work will address some of these limitations. Originality/value The model developed from this research can provide value to institutions in making process- and data-driven predictions on students’ academic performances.

scholarly journals An Analysis on Student Academic Performance by Using Decision Tree Models

2018 ◽  
pp. 615-620
Author(s):  
Jastini Mohd. Jamil ◽  
Nurul Farahin Mohd Pauzi ◽  
Izwan Nizal Mohd. Shahara Nee
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Decision Tree ◽  
Large Volume ◽  
Educational Data Mining ◽  
Data Mining Techniques ◽  
Student Academic Performance ◽  
Tree Models ◽  
Student’S Performance ◽  
Using Data

Large volume of educational data has led to more challenging in predicting student’s performance. In Malaysia currently, study about the performance of students in Malaysia institutions is very little being addressed. The previous studies are still insufficient to identify what factors contribute to student’s achievements and lack of investigations on exploring pattern of student’s behaviour that affecting their academic performance within Malaysia context. Therefore, predicting student’s academic performance by using decision trees is proposed to improve student’s achievements more effectively. The main objective of this paper is to provide an overview on predicting student’s academic performance using by using data mining techniques. This paper also focuses on identifying the pattern of student’s behaviour and the most important attributes that impact to the student’s achievement. By using educational data mining techniques, the students, lecturers and academic institution are able to have a better understanding on the student’s achievement.

scholarly journals Towards reliable prediction of academic performance of architecture students using data mining techniques

2018 ◽  
Vol 16 (3) ◽  
pp. 385-397 ◽  
Author(s):  
Ralph Olusola Aluko ◽  
Emmanuel Itodo Daniel ◽  
Olalekan Shamsideen Oshodi ◽  
Clinton Ohis Aigbavboa ◽  
Abiodun Olatunji Abisuga
Keyword(s):  
Data Mining ◽  
Academic Achievement ◽  
Logistic Regression ◽  
Academic Performance ◽  
Predictive Accuracy ◽  
Support Vector ◽  
Content Type ◽  
Data Mining Techniques ◽  
Svm Model ◽  
Using Data

Purpose In recent years, there has been a tremendous increase in the number of applicants seeking placements in undergraduate architecture programs. It is important during the selection phase of admission at universities to identify new intakes who possess the capability to succeed. Admission variable (i.e. prior academic achievement) is one of the most important criteria considered during the selection process. This paper aims to investigates the efficacy of using data mining techniques to predict the academic performance of architecture students based on information contained in prior academic achievement. Design/methodology/approach The input variables, i.e. prior academic achievement, were extracted from students’ academic records. Logistic regression and support vector machine (SVM) are the data mining techniques adopted in this study. The collected data were divided into two parts. The first part was used for training the model, while the other part was used to evaluate the predictive accuracy of the developed models. Findings The results revealed that SVM model outperformed the logistic regression model in terms of accuracy. Taken together, it is evident that prior academic achievement is a good predictor of academic performance of architecture students. Research limitations/implications Although the factors affecting academic performance of students are numerous, the present study focuses on the effect of prior academic achievement on academic performance of architecture students. Originality/value The developed SVM model can be used as a decision-making tool for selecting new intakes into the architecture program at Nigerian universities.

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 Comparison of Some Classification Algorithms for the Analysis of Students Academic Performance in Educational Data Mining Using Orange

2021 ◽  
pp. 318-324
Author(s):  
Vanthana V
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Random Forest ◽  
Educational Data Mining ◽  
Evaluation Process ◽  
Support Vector ◽  
Classification Algorithms ◽  
Academic Improvement ◽  
Academic Information ◽  
Tools And Techniques

In the modern education system, many higher education institutions prefer data mining tools and techniques to analyze the academic improvement of their students. To support that many data mining techniques and tools are available. This paper uses the classification concept to analyze the student’s academic performance. This paper presents the comparison result of five classification algorithms – Decision Tree, Naïve Bayesian, K-Nearest Neighbour, Support Vector Machine and Random Forest which is applied to the data collected from three colleges of Assam, India. The data consists of socio-economic, demographic as well as academic information of three hundred students with twenty-four attributes. The data mining tool used was ORANGE. The internal assessment attribute in the continuous evaluation process makes the highest impact in the final semester results of the students in the dataset. The results showed that Random Forest out performs the other classifiers based on accuracy.

Exploring students digital activities and performances through their activities logged in learning management system using educational data mining approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Adel Bessadok ◽  
Ehab Abouzinadah ◽  
Osama Rabie
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Management System ◽  
Learning Management System ◽  
Statistical Significance ◽  
Educational Data Mining ◽  
Data Set ◽  
Content Type ◽  
Learning Management ◽  
The Relationship

Purpose This paper aims to investigate the relationship between the students’ digital activities and their academic performance through two stages. In the first stage, students’ digital activities were studied and clustered based on the attributes of their activity log of learning management system (LMS) data set. In the second stage, the significance of the relationship between these profiles and the associated academic performance was tested statistically. Design/methodology/approach The LMS delivers E-learning courses and keeps track of the students’ activities. Investigating these students’ digital activities became a real challenge. The diversity of students’ involvement in the learning process was proven through the LMS which characterize students’ specific profiles. The Educational Data Mining (EDM) approach was used to discover students’ learning profiles and associated academic performances, where the activity log file exemplified their activities hosted in the LMS. The sample study data is from an undergraduate e-course hosted on the platform of Blackboard LMS offered at a Saudi University during the first semester of the 2019–2020 academic year. The chosen undergraduate course had 25 sections, and the students attending came from science, technology, engineering and math background. Findings Results show three clusters based on the digital activities of the students. The correlation test shows the statistical significance and proves the effect of the student’s profile on his academic performance. The data analysis shows that students with different profiles can still get similar academic performance using LMS. Originality/value This empirical study emphasizes the importance of the EDM approach using clustering techniques which can help the instructor understand how students use the provided LMS content to learn and then can deliver them the best educational experience.

Sign in / Sign up

Export Citation Format

Share Document