Performance Prediction of Students in Higher Education Using Multi-Model Ensemble Approach

Butt, Naveed Anwer; Mahmood, Zafar; Shakeel, Khawar; Alfarhood, Sultan; Safran, Mejdl; Ashraf, Imran

doi:10.1109/access.2023.3336987

Cited by 3 publications

(1 citation statement)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some cases, these combined methods can be more accurate than predictions made by a single model. This insight enriches our understanding and offers a solid reference point for our investigation into the predictive modeling of student performance [20].…”

Section: Related Workmentioning

confidence: 74%

Predictive Analysis of Computer Science Student Performance: An ACM2013 Knowledge Area Approach

Almiman,

Othman

2024

ISI

View full text Add to dashboard Cite

In the realm of Educational Data Mining (EDM), the predictive analysis of student performance has emerged as a pivotal area of interest, particularly within computer science education. This investigation employs machine learning and data mining techniques to project academic outcomes of computer science undergraduates, anchoring its framework on the Association for Computing Machinery's (ACM) 2013 Body of Knowledge (Bok), as delineated in the curriculum guidelines for undergraduate computing programs. Encompassing 18 Knowledge Areas (KAs), each with multiple Knowledge Units (KUs), the ACM2013 guideline serves as a comprehensive scaffold for curriculum development, ensuring an inclusive coverage of essential skills and subjects. Through an analysis of data from 2,756 students across nine years at Qassim University's College of Computer Science, this study aims to pinpoint performance levels across various KAs and semesters. Linear regression models were constructed to predict student performance, with their accuracy evaluated through Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE). The predictive accuracy varied across courses, with "Systems Programming" and "Graduation_1" demonstrating high alignment with actual scores, while courses like "Artificial Intelligence" and "Compiler Design" revealed significant discrepancies. A correlation analysis between predicted and actual scores further assessed the models' precision. Findings underscore the utility of EDM in academic settings, especially for tailoring predictive models that enhance student performance prediction in computer science. The identification of KAs with high predictive accuracy corroborates the curriculum's alignment with student achievements, whereas lower accuracy areas highlight potential gaps in curriculum or pedagogy, offering vital insights for educators and curriculum designers to refine educational strategies and resources for improved student outcomes.

show abstract

Section: Related Workmentioning

confidence: 74%

Predictive Analysis of Computer Science Student Performance: An ACM2013 Knowledge Area Approach

Almiman,

Othman

2024

ISI

View full text Add to dashboard Cite

show abstract

Predicting students’ performance at higher education institutions using a machine learning approach

Mohd Zaki,

Razali,

Awang Kader

et al. 2024

View full text Add to dashboard Cite

PurposeMany studies have examined pre-diploma students' backgrounds and academic performance with results showing that some did not achieve the expected level of competence. This study aims to examine the relationship between students’ demographic characteristics and their academic achievement at the pre-diploma level using machine learning.Design/methodology/approachSecondary data analysis was used in this study, which involved collecting information about 1,052 pre-diploma students enrolled at Universiti Teknologi MARA (UiTM) Pahang Branch between 2017 and 2021. The research procedure was divided into two parts: data collecting and pre-processing, and building the machine learning algorithm, pre-training and testing.FindingsGender, family income, region and achievement in the national secondary school examination (Sijil Pelajaran Malaysia [SPM]) predict academic performance. Female students were 1.2 times more likely to succeed academically. Central region students performed better with a value of 1.26. M40-income students were more likely to excel with an odds ratio of 2.809. Students who excelled in SPM English and Mathematics had a better likelihood of succeeding in higher education.Research limitations/implicationsThis research was limited to pre-diploma students from UiTM Pahang Branch. For better generalizability of the results, future research should include pre-diploma students from other UiTM branches that offer this programme.Practical implicationsThis study is expected to offer insights for policymakers, particularly, the Ministry of Higher Education, in developing a comprehensive policy to improve the tertiary education system by focusing on the fourth Sustainable Development Goal.Social implicationsThese pre-diploma students were found to originate mainly from low- or middle-income families; hence, the programme may help them acquire better jobs and improve their standard of living. Most students enrolling on the pre-diploma performed below excellent at the secondary school level and were therefore given the opportunity to continue studying at a higher level.Originality/valueThis predictive model contributes to guidelines on the minimum requirements for pre-diploma students to gain admission into higher education institutions by ensuring the efficient distribution of resources and equal access to higher education among all communities.

show abstract

Software Engineering Team Evaluation: Decision Support System to Predict the Monitor Team Activities

Dahri,

Chandio,

Laghari

et al. 2024

Preprint

View full text Add to dashboard Cite

Due to rapid changes in user requirements (UR), it is a challenging task for software engineers to cope with the sudden software customization requirements (SSCR). The incremental process model (IPM) provides a dynamic approach for analysing, designing and implementing a particular software unit (SU), but the successful deployment requires customer satisfaction as per UR by following the SSCR. For example, during each phase every development team member (DTM) is assigned some particular tasks to accomplish, but it is difficult to determine the team members’ behaviour and performance (TMBP). A successful implementation of customized software would provide more opportunities for a particular company to attract a maximum number of users by using SSCR. Some very nice approaches have been seen over the past two decades to predict DTM to assess their accomplished activities TMBP. This paper proposes a system by offering three layered methodology where first layer is designed for data pre-processing and in the second layer construct the decision model by using ensemble machine-learning technique however the third layer used for result visualization. This paper contributes (a) a novel decision support system to understand the TMBP for the waterfall process model (b) IPM and (c) best classification accuracy 94.14%.

show abstract

Performance Prediction of Students in Higher Education Using Multi-Model Ensemble Approach

Cited by 3 publications

References 68 publications

Predictive Analysis of Computer Science Student Performance: An ACM2013 Knowledge Area Approach

Predictive Analysis of Computer Science Student Performance: An ACM2013 Knowledge Area Approach

Predicting students’ performance at higher education institutions using a machine learning approach

Software Engineering Team Evaluation: Decision Support System to Predict the Monitor Team Activities

Contact Info

Product

Resources

About