E-Assessment and Computer-Aided Prediction Methodology for Student Admission Test Score

Usman, Muhammad; Iqbal, Muhammad Munwar; Iqbal, Zeshan; Chaudhry, Muhammad Umar; Farhan, Muhammad; Ashraf, Muhammad Ikram

doi:10.12973/eurasia.2017.00939a

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first stage of the literature review, we found that only a single technique was used to analyze student educational data in many approaches that are frequently used. For example, Usman et al (2017) tools were developed to predict student entry tests using regression technique. They used demographic data obtained from 5,042 students at the University of Engineering and Technology, Pakistan such as academic data, age, gender, and interests.…”

Section: Applying Machine Learning To Predict Student Performancementioning

confidence: 99%

“…In an educational context, machine learning techniques are a potential approach widely used to accomplish the problems of predicting education outcomes, forecasting student behavior and improving educational quality. This is primarily applied to predict and support decision-making such as analyzing student behavior demography (Bilal et al, 2022;Kaensar & Wongnin, 2023), predicting student performance (Usman et al, 2017;Yagci, 2022), and identifying the relationship between student data and their achievement (Chang & Wang, 2016;Qahmash et al, 2023). However, although those published works could provide educational benefits, those features, and the experimental results tend to be quite limited.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting new student performances and identifying important attributes of admission data using machine learning techniques with hyperparameter tuning

Kaensar,

Wongnin

2023

EURASIA J Math Sci Tech Ed

View full text Add to dashboard Cite

Recently, many global universities have faced high student failure and early dropout rates reflecting on the quality of education. To tackle this problem, forecasting student success as early as possible with machine learning is one of the most important approaches used in modern universities. Thus, this study aims to analyze and compare models for the early prediction of student performance with six machine learning based on Thailand’s education curriculum. A large dataset was collected from the admission scores of 5,919 students during 2011-2021 of 10 programs in the Faculty of Science at Ubon Ratchathani University. The methodology was carried out using Jupyter Notebook, Python 3, and Scikit-Learn to build the models for prediction. To obtain a higher result, we needed not only to find high-performance prediction models, but also to tune hyperparameter configurations consisting of 138 possible different patterns to identify the best-tuned model for each classifier. Furthermore, we investigated significantly important predictors affecting student success for 10 programs in our faculty. In the experiments, the process was divided into two parts: First, we evaluated effective models using a confusion matrix with 10-fold cross-validation. The results showed that random forest (RF) had the highest F1-measure of 86.87%. While predictive models using fine-tuned RF of 10 programs claimed accuracy of about 72% to 93%. Second, we computed the importance of each feature with fine-tuned RF classifiers. The result showed that national test scores (e.g., ONET-English, ONET-Math, ONET-Science, ONET-Social studies, ONET-Thai, and PAT2), entry type, and school grade (e.g., art, English, GPA, health, math, science, and technology) are highly influential features for predicting student success. In summary, these results yield many benefits for other relevant educational institutions to enhance student performance, plan class strategies and undertake decision-making processes.

show abstract

Section: Applying Machine Learning To Predict Student Performancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting new student performances and identifying important attributes of admission data using machine learning techniques with hyperparameter tuning

Kaensar,

Wongnin

2023

EURASIA J Math Sci Tech Ed

View full text Add to dashboard Cite

show abstract

Rethinking student admission and access in higher education through the lens of capabilities approach

Mahlangu

2019

IJEM

View full text Add to dashboard Cite

Purpose The purpose of this paper is to contribute to the scholarship of diversity, equity and inclusivity in higher education. The focus is to advance an understanding of the issues concerning student admissions and access in higher education. The paper will contribute to the debate on student admissions and access in higher education. Among others, the author argues that in the context of higher education, access has different meanings. Design/methodology/approach This paper is conceptual in approach and draws from extant literature and the review was used in compiling the paper. Interpretivist approach was used in understanding the topic. Relying on capabilities approach (CA) as a lens in understanding student admissions and access, the author argues that higher education institutions (HEIs) should consider opportunities (capabilities) for all students to live the lives that they have reason to value (valued functionings). CA works from the premise that human beings share universal capabilities and students’ life can be fulfilling if given the opportunity to exercise their capabilities by universities. Findings Universities can rely on students’ racial and ethnic backgrounds, socioeconomic status and students’ disabilities in admitting them. Diversity characteristics can be used as a tool to ensure the heterogeneity of the student population or as an unfair advantage given to students who might otherwise be deemed inadmissible on the basis of their academic or test performance. Factors such as changing demographics, public policy, institutional practices and marketing techniques seem to have a subtle influence on the process of admission. Students may experience challenges because of the “invisibility” of their disabilities due to a breakdown in communication within higher education systems. Research limitations/implications The paper relied on literature review only and this is its limitation. Literature review may have been influenced by selection bias of the author and is likely to include only those sources that are most consistent with the author’s personal opinion. Selection bias can arise when the inclusion and exclusion criteria for the review are not clearly stated and that might bias the findings. Practical implications Admission officials in HEIs are expected to conduct a diversity needs assessment before admissions with the aim of using the data to identify student population. The needs assessment can look at aspects such as the students’ racial and ethnic backgrounds, socioeconomic status and students’ disabilities to ensure access and success of all students. Social implications Inequities around access and admission for diverse groups of students in higher education are a reality worldwide. There is a worldwide trend within countries to see universities as contributors to economic growth, and many institutions are now increasingly attuned to the money economy. A student’s decision to apply on where to study may be influenced by the reputation of the institution. Originality/value This concept is relative and has different meanings depending on the nature of the work in question. The paper was compiled through literature review, all the sources used have been acknowledged, and the paper conveys the thoughts, interpretations and ideas of the author.

show abstract

E-Assessment and Computer-Aided Prediction Methodology for Student Admission Test Score

Cited by 2 publications

References 14 publications

Predicting new student performances and identifying important attributes of admission data using machine learning techniques with hyperparameter tuning

Predicting new student performances and identifying important attributes of admission data using machine learning techniques with hyperparameter tuning

Rethinking student admission and access in higher education through the lens of capabilities approach

Contact Info

Product

Resources

About