Student advising decision to predict student's future GPA based on Genetic Fuzzimetric Technique (GFT)

Kouatli, Issam

doi:10.1109/fuzz-ieee.2015.7337925

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from the above discussed commonly used techniques and algorithms for prediction of student performance, other techniques that have been used include multi-layer perception (Ramesh et al , 2013), fuzzy logic (Kouatli, 2015), genetic algorithms and R programming (Xing et al , 2015; Kouatli, 2015). However, DT is the most commonly used classification technique in the studies examined because of its speed and non-linear ability when building and testing of the algorithm as well as the ability to combined into an ensemble and create some of the best binary classifiers.…”

Section: Related Literaturementioning

confidence: 99%

Predicting student academic performance using multi-model heterogeneous ensemble approach

Adejo

Connolly

2018

JARHE

View full text Add to dashboard Cite

Purpose The purpose of this paper is to empirically investigate and compare the use of multiple data sources, different classifiers and ensembles of classifiers technique in predicting student academic performance. The study will compare the performance and efficiency of ensemble techniques that make use of different combination of data sources with that of base classifiers with single data source. Design/methodology/approach Using a quantitative research methodology, data samples of 141 learners enrolled in the University of the West of Scotland were extracted from the institution’s databases and also collected through survey questionnaire. The research focused on three data sources: student record system, learning management system and survey, and also used three state-of-art data mining classifiers, namely, decision tree, artificial neural network and support vector machine for the modeling. In addition, the ensembles of these base classifiers were used in the student performance prediction and the performances of the seven different models developed were compared using six different evaluation metrics. Findings The results show that the approach of using multiple data sources along with heterogeneous ensemble techniques is very efficient and accurate in prediction of student performance as well as help in proper identification of student at risk of attrition. Practical implications The approach proposed in this study will help the educational administrators and policy makers working within educational sector in the development of new policies and curriculum on higher education that are relevant to student retention. In addition, the general implications of this research to practice is its ability to accurately help in early identification of students at risk of dropping out of HE from the combination of data sources so that necessary support and intervention can be provided. Originality/value The research empirically investigated and compared the performance accuracy and efficiency of single classifiers and ensemble of classifiers that make use of single and multiple data sources. The study has developed a novel hybrid model that can be used for predicting student performance that is high in accuracy and efficient in performance. Generally, this research study advances the understanding of the application of ensemble techniques to predicting student performance using learner data and has successfully addressed these fundamental questions: What combination of variables will accurately predict student academic performance? What is the potential of the use of stacking ensemble techniques in accurately predicting student academic performance?

show abstract

Section: Related Literaturementioning

confidence: 99%

Predicting student academic performance using multi-model heterogeneous ensemble approach

Adejo

Connolly

2018

JARHE

View full text Add to dashboard Cite

show abstract

“…Shana and Abdullah (2014) described the design and creation of electronic Academic Advisor System termed as SAAS to support conventional procedures of a human advisor. Kouatli (2015) used hybrid intelligent technique composed of fuzzy logic and, genetic Algorithm to prototype a decision support system to predict the future GPA level for students during the admission process depending on the student performance of high school, sophomore exam and an English exam. Nguyen ( 2016) also used a prediction method of academic outcome in math related courses where the multiregression analysis was used to correlate the relationship between learning approached and demographic factors.…”

Section: Academic Advisor System: a Student Questionnairementioning

confidence: 99%

The need for social and academic responsibility advisor (SARA): a catalyst toward the sustainability of educational institutes

Kouatli

2019

SRJ

Self Cite

View full text Add to dashboard Cite

Purpose The purpose of this paper is to investigate elements of socio-academic-related sustainability in educational institutes and propose a structure of an advising system that can aid the most critical stakeholders in such educational institutes, i.e the student. Hence, after reviewing the contemporary University Social Responsibility (USR) Venn diagram, the paper focuses on the need to develop a social and academic responsibility advisor (SARA) system as a catalyst toward fulfilling social responsibility to the most important stakeholder and alternatively leads to enhanced sustainability of such educational institutes. Design/methodology/approach A combination of research methods used in this paper, defined as by identifying the need for SARA from a literature survey. By distributing a questionnaire to students investigating their desire of an academic advisor system and by establishing a focus group to study the academic and social aspects and its implications to students’ “quality of life” as an essential aspect toward the educational institutes' sustainability. Various issues related to the features of the SARA discussed. Findings Literature review shows only a few articles combine both aspects of advising activities (social and academic), most of which are not interrelated to the sustainability of educational institutes. This paper highlights the need and connectivity of SARA to contemporary USR sustainability. The descriptive statistics of the questionnaire showed about 86 per cent of student participants interested in applying the proposed features. The outcome of the focus group resulted in more detailed features of academic and social aspects of the expected SARA system. Research limitations/implications The proposed features of SARA described where the inter-related social and academic activities could be managed, logged and used by students. The proposed “heterogeneous study group” was investigated by observation implemented in four different courses in two different semesters. The result was not conclusive, and further study recommended. Even though this experimentation was not conclusive, the lesson learned from this study highlighted different issues associated with “study groups” within a course. Practical implications Applicability of SARA would enhance the quality of life of students in general and provide a mechanism to motivate low aptitude students to get engaged with study and projects with high-aptitude students. Social implications Avoiding the “feel” of isolation by some students due to the inability to find study partner who can also act as mentor to a study group. The proposed “Heterogeneous study group” would provide a mechanism for “Practiced student-to-student Social responsibility”. Originality/value The paper highlights and proves the need for SARA in contemporary USR where SARA can act as a catalyst for enhancing the socio-academic zone of the reviewed USR Venn diagram. Features of SARA identified as an outcome of the study in this paper. Proposal of “Heterogeneous Study Group” was proposed as mechanism of “social learning”. “Group health” testing was proposed as a criteria resulted from a balance between collaboration, social affinity and project effort.

show abstract

Vector Decoupling Control Design Based on Genetic Algorithm for a Residential Microgrid System for Future City Houses at Islanding Operation

et al. 2018

View full text Add to dashboard Cite

Student advising decision to predict student's future GPA based on Genetic Fuzzimetric Technique (GFT)

Cited by 5 publications

References 13 publications

Predicting student academic performance using multi-model heterogeneous ensemble approach

Predicting student academic performance using multi-model heterogeneous ensemble approach

The need for social and academic responsibility advisor (SARA): a catalyst toward the sustainability of educational institutes

Vector Decoupling Control Design Based on Genetic Algorithm for a Residential Microgrid System for Future City Houses at Islanding Operation

Contact Info

Product

Resources

About