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

Aluko, Ralph Olusola; Daniel, Emmanuel Itodo; Oshodi, Olalekan Shamsideen; Aigbavboa, Clinton; Abisuga, Abiodun Olatunji

doi:10.1108/jedt-08-2017-0081

Cited by 33 publications

(33 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Though, this finding seems not contradictory to the earlier reported ones as both high school grades and the ongoing semester course grades still refer to prior academic achievement of the students in some sense. The findings reported by Aluko, Daniel, Oshodi, Aigbavboa and Abisuga (2018); Opstad, Bonesrønning and Fallan (2017) corroborate this point. Aluko et al (2018) utilised more sophisticated statistical tools such as logistic regression and support vector machine learning to establish high correction between prior academic achievement and performance.…”

Section: Introductionmentioning

confidence: 60%

“…university (Ayán & García, 2008), high school students (Casillas et al, 2012); the field of study, e.g. accounting (Duff 2004), mathematics (Hailikari et al, 2008), economics (Opstad et al, 2017), and architecture (Aluko et al, 2018). In several of these studies, researchers have used students' test scores on standardised tests, high school grades and entrance exams (Aluko et al, 2018;Casillas et al, 2012;Duff 2004;Newman Ford et al, 2009) while others have used students previous semester/year grades (Ayán & García, 2008;Engerman & Bailey, 2006;Martin et al, 2016;Zakariya, 2016) or a special exam on problem-solving (Hailikari et al, 2008) to assess prior knowledge.…”

Section: The Conceptualisation Of Prior Knowledgementioning

confidence: 99%

See 1 more Smart Citation

Assessing first-year engineering students' pre-university mathematics knowledge: Preliminary validity results based on an item response theory model

Zakariya

Nilsen

Goodchild

et al. 2020

J. Technol. Sci. Educ.

View full text Add to dashboard Cite

The importance of students’ prior knowledge to their current learning outcomes cannot be overemphasised. Students with adequate prior knowledge are better prepared for the current learning materials than those without the knowledge. However, assessment of engineering students' prior mathematics knowledge has been beset with a lack of uniformity in measuring instruments and inadequate validity studies. This study attempts to provide evidence of validity and reliability of a Norwegian national test of prior mathematics knowledge using an explanatory sequential mixed-methods approach. This approach involves use of an item response theory model followed by cognitive interviews of some students among 201 first-year engineering students that constitute the sample of the study. The findings confirm an acceptable construct validity for the test with reliable items and a high-reliability coefficient of .92 on the whole test. Mixed results are found on discrimination and difficulty indices of questions on the test with some questions having unacceptable discriminations and require improvement, some are easy, and some appear too tricky questions for students. Results from the cognitive interviews reveal the likely reasons for students' difficulty on some questions to be lack of proper understanding of the questions, text misreading, improper grasping of word-problem tasks, and unavailability of calculators. The findings underscore the significance of validity and reliability checks of test instruments and their effect on scoring and computing aggregate scores. The methodological approaches to validity and reliability checks in the present study can be applied to other national contexts.

show abstract

Section: Introductionmentioning

confidence: 60%

Section: The Conceptualisation Of Prior Knowledgementioning

confidence: 99%

Assessing first-year engineering students' pre-university mathematics knowledge: Preliminary validity results based on an item response theory model

Zakariya

Nilsen

Goodchild

et al. 2020

J. Technol. Sci. Educ.

View full text Add to dashboard Cite

show abstract

“…Using pre-enrollment features to predict students' academic achievement is significant, especially if the prediction is to be performed at an early stage (Alturki et al, 2020). Previous GPA is one of the most popular used features for predicting academic success (Abu Saa, 2016;Aluko et al, 2018;Garg, 2018;Huang & Fang, 2013;Kabakchieva, 2013;Kovačić, 2010;Osmanbegović & Suljic, 2012;Pal & Pal, 2013;Thai-Nghe et al, 2007). Academic language skills have also been widely used for predicting academic success (Abu Saa, 2016;Asif et al, 2017;Badr et al, 2016;Bani-Salameh, 2018;Thai-Nghe et al, 2007).…”

Section: Related Work On Predictions In Higher Educationmentioning

confidence: 99%

Using Educational Data Mining to Predict Students’ Academic Performance for Applying Early Interventions

Alturki

2021

JITE:IIP

View full text Add to dashboard Cite

Aim/Purpose: One of the main objectives of higher education institutions is to provide a high-quality education to their students and reduce dropout rates. This can be achieved by predicting students’ academic achievement early using Educational Data Mining (EDM). This study aims to predict students’ final grades and identify honorary students at an early stage. Background: EDM research has emerged as an exciting research area, which can unfold valuable knowledge from educational databases for many purposes, such as identifying the dropouts and students who need special attention and discovering honorary students for allocating scholarships. Methodology: In this work, we have collected 300 undergraduate students’ records from three departments of a Computer and Information Science College at a university located in Saudi Arabia. We compared the performance of six data mining methods in predicting academic achievement. Those methods are C4.5, Simple CART, LADTree, Naïve Bayes, Bayes Net with ADTree, and Random Forest. Contribution: We tested the significance of correlation attribute predictors using four different methods. We found 9 out of 18 proposed features with a significant correlation for predicting students’ academic achievement after their 4th semester. Those features are student GPA during the first four semesters, the number of failed courses during the first four semesters, and the grades of three core courses, i.e., database fundamentals, programming language (1), and computer network fundamentals. Findings: The empirical results show the following: (i) the main features that can predict students’ academic achievement are the student GPA during the first four semesters, the number of failed courses during the first four semesters, and the grades of three core courses; (ii) Naïve Bayes classifier performed better than Tree-based Models in predicting students’ academic achievement in general, however, Random Forest outperformed Naïve Bayes in predicting honorary students; (iii) English language skills do not play an essential role in students’ success at the college of Computer and Information Sciences; and (iv) studying an orientation year does not contribute to students’ success. Recommendations for Practitioners: We would recommend instructors to consider using EDM in predicting students’ academic achievement and benefit from that in customizing students’ learning experience based on their different needs. Recommendation for Researchers: We would highly endorse that researchers apply more EDM studies across various universities and compare between them. For example, future research could investigate the effects of offering tutoring sessions for students who fail core courses in their first semesters, examine the role of language skills in social science programs, and examine the role of the orientation year in other programs. Impact on Society: The prediction of academic performance can help both teachers and students in many ways. It also enables the early discovery of honorary students. Thus, well-deserved opportunities can be offered; for example, scholarships, internships, and workshops. It can also help identify students who require special attention to take an appropriate intervention at the earliest stage possible. Moreover, instructors can be aware of each student’s capability and customize the teaching tasks based on students’ needs. Future Research: For future work, the experiment can be repeated with a larger dataset. It could also be extended with more distinctive attributes to reach more accurate results that are useful for improving the students’ learning outcomes. Moreover, experiments could be done using other data mining algorithms to get a broader approach and more valuable and accurate outputs.

show abstract

“…Aluko, Daniel, Shamsideen Oshodi, Aigbavboa, & Abisuga, [3] compared the prediction accuracy of Support vector machine and logistic regression using a sample size of 102 architecture students for predicting the performance of students in academics and found that Support vector machine classifier is better than logistic regression in predicting students' academic performance. Umer, Susnjak, Mathrani, & Suriadi, [14] have used three Machine learning classification algorithms to predict the performance of students by recording their weekly performance in MOOCS environment.…”

Section: Review Of Literaturementioning

confidence: 99%

Modelling a Machine Learning Classifier for Predicting Student’s Entrepreneurial Intentions

Raj¹,

Manivannan²

2021

INDJCSE

View full text Add to dashboard Cite

Entrepreneurship study and research is an important aspect in booming economy like India because entrepreneurs provide necessary impetus and act as a catalyst in bringing economic growth. In this study we have designed a logistic regression based predictive classification algorithm to predict entrepreneurship affinity to start a new business. The Logistic Model uses a binary categorical variable i.e., interest towards starting a business in near future (Sure or Not Sure) as dependent variable and socio-economic factors, behavioural traits i.e., Risk bearing capacity, Creativity, Decision Making capacity, Leadership ability, Ease of Communication, Self-confidence, and Willingness to enter unfamiliar territory as independent variables. The Model also compares various feature selection methods in improving predictive accuracy. Data is collected from 321 students using a structured questionnaire and model predicts the significant factors that impact the entrepreneurship decision and probability of students having positive attitude towards starting a new business. Findings from the study revealed that the Gender of the respondents, attitude towards entrepreneurship and risk bearing capacity as the significant factors impacting the student's intent towards starting a new business in near future.

show abstract

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

Cited by 33 publications

References 54 publications

Assessing first-year engineering students' pre-university mathematics knowledge: Preliminary validity results based on an item response theory model

Assessing first-year engineering students' pre-university mathematics knowledge: Preliminary validity results based on an item response theory model

Using Educational Data Mining to Predict Students’ Academic Performance for Applying Early Interventions

Modelling a Machine Learning Classifier for Predicting Student’s Entrepreneurial Intentions

Contact Info

Product

Resources

About