scholarly journals Prediction of Student Performance using Hybrid Classification

2019 ◽  
Vol 8 (4) ◽  
pp. 6566-6570
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Student Performance ◽  
Research Work ◽  
Educational Data Mining ◽  
Classification Algorithm ◽  
Classification Algorithms ◽  
Data Types ◽  
Data Set ◽  
Hybrid Classification

Data mining technologies allow collection, storage and processing huge amounts of data and carrying a large variety of data types and samples. Predicting academic performance of student is the most successive research in this era. Previous research work researchers are used different classification algorithm to predict the student performance. There is lot of research work to be taken in the field of educational data mining and big data in education to increase the accuracy of the classification algorithm and predict the academic performance of student. In this research work we used hybrid classification algorithm for predicting the performance of students. Two Popular classification algorithms ID3 and J48 were applied on the data set. To make hybrid classification voting technique is applied using weka machine learning tool. In this work we tested how the hybrid algorithm accurately predicts the student data set. To check the predicted result classification accuracy was computed. This hybrid classification algorithm gives accuracy with 62.67%.

scholarly journals The uses of educational data mining in academic performance analysis at higher education institutions (case study at UNJANI)

2021 ◽  
Vol 11 (1) ◽  
pp. 26-35
Author(s):  
Yulison Herry Chrisnanto ◽  
◽  
Gunawan Abdullah ◽  
Keyword(s):  
Higher Education ◽  
Data Mining ◽  
Academic Performance ◽  
Student Performance ◽  
Higher Education Institutions ◽  
Educational Data Mining ◽  
Strategic Decision ◽  
Data Set ◽  
Study Results ◽  
Mining Model

Education is an important thing in a person's life, because by having adequate education, one's life will be better. Education can be obtained formally through formal institutions that constructively provide a person's abilities academically. This study aims to determine student performance in terms of academic and non-academic domains at a certain time during their education using techniques in data mining (DM) which are directed towards academic data analysis. Academic performance is delivered through the Educational Data Mining (EDM) integrated data mining model, in which the techniques used include classification (ID3, SVM), clustering (k-Means, k-Medoids), association rules (Apriori) and anomaly detection (DBSCAN). The data set used is academic data in the form of study results over a certain period of time. The results of EDM can be used for analysis related to academic performance which can be used for strategic decision making in aca-demic management at higher education institutions. The results of this study indicate that the use of several techniques in data mining together can maximize the ability to analyze academic performance with the same data source and produce different analysis patterns.

scholarly journals Classifiers ensemble and synthetic minority oversampling techniques for academic performance prediction

2019 ◽  
Vol 8 (3) ◽  
pp. 122
Author(s):  
Abdulazeez Yusuf ◽  
Ayuba John
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Research Work ◽  
Educational Data Mining ◽  
Sampling Technique ◽  
Ensemble Model ◽  
Data Set ◽  
Grade Point ◽  
Matriculation Examination ◽  
The Individual

The increasing need for data driven decision making recently has resulted in the application of data mining in various fields including the educational sector which is referred to as educational data mining. The need for improving the performance of data mining models has also been identified as a gap for future researcher. In Nigeria, higher educational institutions collect various students’ data, but these data are rarely used in any decision or policy making to improve the academic performance of students. This research work, attempts to improve the performance of data mining models for predicting students’ academic performance using stacking classifiers ensemble and synthetic minority over-sampling techniques. The research was conducted by adopting and evaluating the performance of J48, IBK and SMO classifiers. The individual classifiers models, standard stacking classifier ensemble model and stacking classifiers ensemble model were trained and tested on 206 students’ data set from the faculty of science federal university Dutse. Students’ specific previous academic performance records at Unified Tertiary Matriculation Examination, Senior Secondary Certificate Examination and first year Cumulative Grade Point Average of students are used as data inputs in WEKA 3.9.1 data mining tool to predict students’ graduation classes of degrees at undergraduate level. The result shows that application of synthetic minority over-sampling technique for class balancing improves all the various models performance with the proposed modified stacking classifiers ensemble model outperforming the various classifiers models in both performance accuracy and RSME values making it the best model.<strong></strong>

Empirical study on the effect of using synthetic attributes on classification algorithms

2017 ◽  
Vol 10 (2) ◽  
pp. 111-129 ◽  
Author(s):  
Ali Hasan Alsaffar
Keyword(s):  
Data Mining ◽  
Empirical Study ◽  
Student Performance ◽  
Software Tool ◽  
Real Data ◽  
Support Vector ◽  
Classification Algorithms ◽  
Past Performance ◽  
Data Set ◽  
Content Type

Purpose The purpose of this paper is to present an empirical study on the effect of two synthetic attributes to popular classification algorithms on data originating from student transcripts. The attributes represent past performance achievements in a course, which are defined as global performance (GP) and local performance (LP). GP of a course is an aggregated performance achieved by all students who have taken this course, and LP of a course is an aggregated performance achieved in the prerequisite courses by the student taking the course. Design/methodology/approach The paper uses Educational Data Mining techniques to predict student performance in courses, where it identifies the relevant attributes that are the most key influencers for predicting the final grade (performance) and reports the effect of the two suggested attributes on the classification algorithms. As a research paradigm, the paper follows Cross-Industry Standard Process for Data Mining using RapidMiner Studio software tool. Six classification algorithms are experimented: C4.5 and CART Decision Trees, Naive Bayes, k-neighboring, rule-based induction and support vector machines. Findings The outcomes of the paper show that the synthetic attributes have positively improved the performance of the classification algorithms, and also they have been highly ranked according to their influence to the target variable. Originality/value This paper proposes two synthetic attributes that are integrated into real data set. The key motivation is to improve the quality of the data and make classification algorithms perform better. The paper also presents empirical results showing the effect of these attributes on selected classification algorithms.

scholarly journals Prediction and Analysis of Student Performance in Secondary Education Based on Data Mining and Machine Learning Techniques

2020 ◽  
pp. 294-301
Author(s):  
Meenal Joshi ◽  
Shiv Kumar
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Secondary School ◽  
Student Performance ◽  
Learning Algorithms ◽  
Research Work ◽  
Educational Data Mining ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Student’S Performance

<p>According to modern era education is the key to achieve success in the future; it develops a human personality, thoughts, and social skills. The purpose of this research work is to focus on educational data mining (EDM) through machine learning algorithms. EDM means to discover hidden knowledge and pattern about student's performance. Machine learning can be useful to predict the learning outcomes of students. From last few years, several tools have been used to judge the student's performance from different points of view like the student's level, objectives, techniques, algorithms, and different methods. In this paper, predicting and analyzing student performance in secondary school is conducted using data mining techniques and machine learning algorithms such as Naive Bayes, Decision Tree algorithm J48, and Logistic Regression. For this the collection of dataset from "Secondary School" and then filtration is applying on desired values using WEKA, tool.</p>

scholarly journals An Ingenious Methodology for the Collation of Existing Algorithms for the Prognosis of Student Performance

2020 ◽  
Vol 9 (5) ◽  
pp. 1749-1752
Keyword(s):  
Data Mining ◽  
Academic Performance ◽  
Random Forest ◽  
Student Performance ◽  
Naive Bayes ◽  
Research Work ◽  
Large Data ◽  
Naïve Bayes ◽  
Impact Factors ◽  
Data Mining Technique

In this proposed research work we use a profound Data mining technique which is an automated procedure of discovering interesting patterns by means of comprehensible predictive models from large data sets by grouping them. Predicting a student's academic performance is very crucial especially for universities. Educational Data Mining (EDM) is an approach for extricating useful data that could possibly affect a firm. Nowadays student’s performance is swayed by a lot of aspects. These aspects might involve the academic performance of a student. This subject evaluates numerous factors probably suspected to alter a student’s empirical performance in scholastic, and discover a subjective design which classifies and forecast the student’s learning outcomes. The intention of this research is to conduct a case study on factors swayed by the student’s academic achievements and to dictate greater impact factors. In this paper we focus on the academic achievement evaluation on the basis of correct instances and incorrect instances by means of Naive Bayes and Random Forest algorithms. This paper intends to make a metaphorical assessment of Naive Bayes and random Forest classifier on student data and dictate the best algorithm.

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.

scholarly journals Educational Data Classification and prediction using Data Mining Algorithms

2019 ◽  
Vol 8 (3) ◽  
pp. 8674-8678 ◽  
Keyword(s):  
Data Mining ◽  
Random Forest ◽  
Predictive Modeling ◽  
Research Work ◽  
Logical Structure ◽  
Individual Performance ◽  
Mining Machine ◽  
Support Vector ◽  
Classification Algorithms ◽  
Data Set

Data Mining is the process of extraction interesting patterns from huge data sets and converts the patterns into logical structure for further Analysis. Predictive Modeling processes that make use of data mining, Machine learning and probability methods to forecast. Engineering is the most widely accepted stream of education in India. Students are uncertain about which department to join in engineering. It is important to improve the individual performance and help the students make the perfect choice regarding the department. In this paper, the hidden information from the previously recorded enrollment details during admission process is used to solve the students’ uncertainty in their choice of department. In addition to this, the performance of alumnae also needs to be analyzed by the teachers to have a clear idea about the future of existing students. Our main goal is to unravel these problems using predictive Modeling. Here, we are focusing on three classification algorithms namely, support vector machine, Random Forest and Naïve Bayes. Data has been collected, normalized and applied to the three different classification algorithms, from which the best model is formulated using various parameters of evaluation. In this paper, we present our approach towards implementing the best model which is built based on the profession of parents, demographic features, type of location of the student and correlation between high school and higher secondary examinations. The Result of this research work shows that Random forest is efficient for the data set used when compared to the other two Classification algorithms.

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.

scholarly journals Academic Performance based on Gender using Filter Ranker Algorithms - An Experimental Analysis in Sultanate of Oman

2019 ◽  
Vol 8 (11) ◽  
pp. 3502-3506
Keyword(s):  
Academic Performance ◽  
Student Performance ◽  
Data Model ◽  
Predictive Accuracy ◽  
Profile Analysis ◽  
Educational Data Mining ◽  
Drop Out ◽  
Teaching Methodology ◽  
Sultanate Of Oman ◽  
Data Set

Education molds the future society. Student profile analysis in higher education system in sultanate of Oman reveals that drop out cases of students are tremendously increasing for the last few years. Learning environment plays a vital role in providing appropriate teaching methodologies to motivate the skills of the students. Variations in academic performance can be observed based on different educational indicators such as gender, social, economical, cultural and community characteristics. This paper tries to conduct an analysis on the existing data based on educational data mining and tries to make a classification based on gender which helps to adapt necessary teaching methodology to improve the student performance. A data set of 400 students from three colleges in Sultanate of Oman in three consecutive years is taken as case study for this analysis. Since student’s performance is classified as per the data model based on their gender, equal number of male and female data are considered. Data consists of 12 attributes with result as output. Classification of students performance has been achieved using the classification algorithms in WEKA tool. Irrelevant features are eliminated to select subset of input variables in feature selection (FS) algorithm. This is active to improve learning efficiency, predictive accuracy and reduce complexity of learned results. The paper demonstrates gender as the priority attribute to create best data model

scholarly journals Applying Deep Learning Neural Networks in Predicting Students' Cumulative Grades

2020 ◽  
Vol 10 (2) ◽  
pp. 293-297
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Academic Performance ◽  
Deep Learning ◽  
Student Performance ◽  
Quality Education ◽  
Data Set ◽  
Improve Student Performance ◽  
The Difference ◽  
Indirect Information

The distinguished universities aim to provide quality education to their students. One way to achieve the highest quality in university studies is to discover knowledge to predict student performance and grades in courses etc. Recently, the amount of data stored in educational databases is accumulating very quickly, as these databases contain indirect information that can be used to improve student performance. Academic performance is affected by many factors, so it is necessary to predict student performance to determine the difference between students who are excelling in studies and students who need to exert more effort to improve their performance and their level of achievement. Hidden or Indirect knowledge is part of the educational data set and can be extracted using various means, such as data mining techniques and the use of classification, and deep learning through neural networks. This paper has been designed to extract knowledge describing students' performance in the courses required for graduation, in a way that helps academic advisors in providing academic advice and guidance to students to improve their cumulative grades.

Sign in / Sign up

Export Citation Format

Share Document