Predicting student performance in higher education using multi-regression models

The importance of accurately predicting student performance in education, especially in the challenging curricular unit of Introductory Programming, cannot be overstated. As institutions struggle with high failure rates and look for solutions to improve the learning experience, the need for effective prediction methods becomes critical. This study aims to conduct a systematic review of the literature on methods for predicting student performance in higher education, specifically in Introductory Programming, focusing on machine learning algorithms. Through this study, we not only present different applicable algorithms but also evaluate their performance, using identified metrics and considering the applicability in the educational context, specifically in higher education and in Introductory Programming. The results obtained through this study allowed us to identify trends in the literature, such as which machine learning algorithms were most applied in the context of predicting students’ performance in Introductory Programming in higher education, as well as which evaluation metrics and datasets are usually used.

Student enrolment, financial challenges, technology integration, and curriculum diversification have increasingly competition among higher education institutions. The ideal future workforce must possess not only technical expertise but also strong skills in complex problem solving, critical thinking, creativity, human resource management, and teamwork. In addition to analytical and leadership capabilities, these competencies are essential for thriving in a rapidly evolving digital economy. However, limited study has been conducted to assess Indonesia's readiness to engage with this digital transformation. The aim of this study to examine the correlation of 4.0 educational adaptation and school management on student performance in higher education in Borobudur University. This study uses applied research with a cross-sectional design to examine the impact of technological infrastructure and faculty management on student’s performance. The population consists of employee at Borobudur University with a sample 40 respondents including leaders, lecturer and education staff. The result found that, the bivariate analysis of technological infrastructure, strategic planning and policy making, operational management, student assessment have significant relationship with performance. p value 0.000. The final model the variable technological structure significant correlation and operational management as confounding factor of student assessment R 0.603, RR 0,364 (36.4%) VIF 2.955.; Strategic planning and policy making was significant with Student performance and technological infrastructure as confounding factor with student performance R 00,609, R2 0,371 (37.1%), VIF 2,277. Student performance, student assessment significant correlation with Student Performance R 0,460, R2 0211 (21,1%), p 0.003, VIF 1.000. Conclusion technological infrastructure and operational management correlation with student assessment; strategic planning and policy and technological infrastructure correlation with student performance; student performance significant correlation with student performance.

Understanding, modeling, and predicting student performance in higher education poses significant challenges concerning the design of accurate and robust diagnostic models. While numerous studies attempted to develop intelligent classifiers for anticipating student achievement, they overlooked the importance of identifying the key factors that lead to the achieved performance. Such identification is essential to empower program leaders to recognize the strengths and weaknesses of their academic programs, and thereby take the necessary corrective interventions to ameliorate student achievements. To this end, our paper contributes, firstly, a hybrid regression model that optimizes the prediction accuracy of student academic performance, measured as future grades in different courses, and, secondly, an optimized multi-label classifier that predicts the qualitative values for the influence of various factors associated with the obtained student performance. The prediction of student performance is produced by combining three dynamically weighted techniques, namely collaborative filtering, fuzzy set rules, and Lasso linear regression. However, the multi-label prediction of the influential factors is generated using an optimized self-organizing map. We empirically investigate and demonstrate the effectiveness of our entire approach on seven publicly available and varying datasets. The experimental results show considerable improvements compared to single baseline models (e.g. linear regression, matrix factorization), demonstrating the practicality of the proposed approach in pinpointing multiple factors impacting student performance. As future works, this research emphasizes the need to predict the student attainment of learning outcomes.

Aim/Purpose: The main objective of this study is to explore students’ beliefs with regard to social media use (SMU) in higher education and the consequences of such use on the perception of their academic performance. Additionally, the study aims to determine the major influential factors with regard to SMU in student learning settings as a means of enhancing their performance. To achieve these objectives, drawing on the literature related to SMU in higher education settings, a research model has been developed. Background: Social media platforms have led to a significant transformation with regard to the communication landscape in higher education in terms of offering enhanced learning and improved teaching experience. Nevertheless, little is known, particularly in developing countries such as Jordan, as to whether or not the use of such platforms by students in higher education increases the perceptions of their academic performance. Therefore, this study has developed a model to examine the perceptions of higher education students with regard to social media use and its effect on their performance. Methodology: The Structural Equation Modelling approach is used to analyze data collected via an online survey in the form of a questionnaire to examine the use of such a model. The study sample is drawn from undergraduate and postgraduate students from three universities (one public and two private) in Jordan. Convenience sampling is used to collect data. Out of 730 sent questionnaire, 513 responses were received, of which 403 were deemed qualified to be part of the data analysis process. Contribution: This study contributes to the literature on social media in higher education by enhancing our understanding of the perceptions of higher education students on the use of social media in their learning. The tested model can be used as a benchmark for other studies that target the impact of social media on student performance in higher education. Findings: The results reveal that perceptions of (1) usefulness, collaborative learning, enhanced communication, enjoyment, and ease of use of social media have a positive effect on the use of such media in student learning; (2) resource sharing has an insignificant effect on social media use in student learning, and (3) social media use has a positive influence on students’ perceptions of their academic performance. Recommendations for Practitioners: Senior management and policy makers in higher education institutions will have to train faculty members on effective strategies and methods in order to effectively integrate social media into education. This would equip faculty members with the necessary digital skills needed to help them to be fully informed regarding the benefits of social media and its tools in learning and teaching activities and would also allow them to avoid any possible drawbacks. Furthermore, faculty members should reconsider their current techniques and strategies, and adopt new methods in their teaching that encourage students to use social media platforms as part of their learning. For example, they can regularly post discussions and assignments on social media platforms to inculcate the habit of using such platforms among students for educational purposes. Students, on the other hand, should be aware of the implications and potential advantageous aspects of SMU in their learning. This could be done by conducting regular workshops and seminars in the various faculties and schools at universities. Recommendation for Researchers: Researchers are encouraged to investigate additional factors that might influence the use of social media by students as well as faculty members. Specially, an emphasis should be given to identify any potential obstacles that might hinder the use of social media in higher education. Impact on Society: Social media is not only useful for socializing, but also it can be an effective educational tool that enhance students’ performance in higher education. Future Research: Although the collected data support the research model, this study is subjected to various limitations that need to be tackled by further studies. This study is based on the principles of quantitative research design. Data for this study was collected via survey questionnaires. Accordingly, future studies may consider a qualitative research design in order to uncover additional factors that may impact the use of social media on the part of higher education students. This would allow researchers to generate in-depth insights and a holistic understanding of SMU by higher education students. A convenience sampling method was employed to select respondents for this study. The respondents who participated in this study were from three universities (one public and two private) in Jordan. Accordingly, future research is deemed to be necessary to achieve a degree of generalizability regarding the findings of this study.

This study investigates the predictive power of learning management system (LMS) log data for student performance in higher education. Analyzing interactions from 114 students in a sports pedagogy course, we compared linear regression (LR), random forest regression (RFR), and support vector regression (SVR), each paired with mutual information (MI) and backward elimination (BE) feature selection. Results show LMS log data alone can effectively predict final grades, with SVR[Formula: see text]BE performing best ([Formula: see text], MAE [Formula: see text] 4.54). Feature selection, particularly BE, consistently improved model performance across all algorithms. Key findings include: LMS interactions strongly predict academic performance; SVR outperforms other algorithms in capturing complex educational data relationships; and BE’s superiority highlights the importance of feature interactions. This research advances educational data mining (EDM) by identifying optimal modeling approaches for LMS data, contributing to the development of early warning systems in online and blended learning environments.

Since the creation of the European Higher Education Area (EHEA) in 1999, the development of new teaching models, in which the student takes responsibility for their learning, has been favored. In this educational context, pedagogical leadership, understood as that oriented to the improvement of student achievement and performance, is presented as a response capable of promoting and improving both the quality of higher education and the teaching–learning processes. This study is intended to analyze the incidence of pedagogical leadership in higher education institutions from the most current scientific literature. Pedagogical leadership can be defined as a leadership that will have an influence on the student’s performance. For this, a systematic review was carried out in the Web of Science and Scopus databases. Seventeen of the 288 articles reviewed were accepted. Therefore, the representation in the scientific literature of leadership aimed at improving student performance in higher education is still limited and incipient. As main contributions, the need to incorporate this leadership model in higher education institutions is highlighted, as an element of change and improvement of quality in them, as well as to evaluate the results obtained after its incorporation in higher education.

The thesis “Student Performance in Higher Education: Ability, Class Attendance, Mobility and the Bologna Process” empirically analyzes determinants of students’ success at university. Administrative student data as well as survey data collected at Göttingen University, Germany are used. Chapter 2 identifies individual and institutional factors, for example the high school leaving grade or the faculty a student is enrolled at, and analyzes their impact on academic performance. In this context, academic performance is measured in three dimensions: the probability of obtaining any degree at university, the probability of obtaining a degree within a chosen field of study and the grade of the final university degree. Two main results emerge: Firstly, the high school leaving grade is by far the most important individual determinant of students’ success at university. In contrast, criteria such as social origin or gender only play a minor role. Secondly, there are substantial differences between faculties implying that institutional factors also influence academic performance. Chapter 3 evaluates whether attending the lecture and/or tutorial in two basic courses in business administration and economics has an impact on the achieved grade. The analysis finds no significant effect of class attendance on university performance in most specifications. Although identifying a causal effect may not be possible with the data at hand, the result allows the conclusion that going to class and studying on one’s own may be substitutes in the given framework. Chapter 4 focuses on bachelor students to analyze whether a study-related visit abroad influences university outcomes. In this context, university outcomes are measured by the final grade of the bachelor degree and the probability of graduating within the standard time period. A propensity score matching strategy is applied to overcome the potential problem of self-selection into studying abroad. The analysis shows that a sojourn improves the final university grade. However, the result seems mainly to be driven by selective transferring of grades. In addition, bachelor students who do a study-related visit abroad have a lower probability of graduating within the standard time period than their peers who stay at the home institution. This supports the idea that students do not count all grades achieved abroad towards their degree at home. Finally, Chapter 5 is devoted to the Bologna process. It evaluates the effect of replacing traditional five-year degrees (Magister, Diplom, old teacher degree) with three-year bachelor programs on the duration until graduation and the timing of university drop-out. Competing risks models are estimated using a relative time measure that makes information on duration between old and new study programs comparable. The analysis shows that the Bologna process reduced the duration until students achieve their first university degree both in absolute and relative terms. However, concerning the timing of university drop-out, the results are less conclusive. Only for the faculty of humanities there is a clear effect of the Bologna process on the probability of dropping out of university.

PurposeThe study aims to explore factors that influence students’ academic performance in the context of physical ergonomics and assess the mediating effect of motivation between lighting, noise, temperature, chair design and students’ performance from the student’s perspective.Design/methodology/approachThe research was categorised as a correlational study and employed non-contrived and cross-sectional methods to achieve its objectives. The target population was university students aged 18 years old and above enrolled in Malaysia’s higher education institutions. Due to the inaccessibility of the sample frame, convenience sampling, a type of non-probability sampling, was utilised. Data collection was conducted through an online survey primarily distributed among student groups.FindingsThe study’s findings reveal that only two exogenous variables, lighting and noise, directly influence students' performance. Additionally, motivation is a potent and significant factor in shaping students' performance. Motivation is also identified as a mediator in the complex relationship between lighting, noise, temperature and student performance. Surprisingly, although temperature does not directly influence student performance, it indirectly influences performance through motivation.Originality/valueThis study is an original exploration into the intricate factors shaping students' academic performance within the domain of physical ergonomics from a student perspective. The research uniquely investigates the mediating impact of motivation on the relationships between lighting, noise, temperature, seating arrangements and academic outcomes. The findings will contribute novel insights to the existing body of knowledge, offering a distinct perspective on the complex dynamics that influence student learning experiences and performance in educational settings.

This research study aims to evaluate the significance of Technology and Industry 4.0 for Student Performance in Higher Education. Industry 4.0 is part of digital revolution which amalgamates various technologies like AI, distributed computing, virtual reality (VR), Internet of Things (IoT) & Big Data to bring a fundamental transformation in the current industry. The integration of these technologies has benefited all domains of society including Education. Education 4.0 aims to use Industry Revolution 4.0 technologies to the benefit of education field by providing means to improve the education sector using techniques like Education Mining, Prediction and Prescription of student's performance during their learning duration at universities. This study tries to highlight some important literature in the area of Industrial Revolution 4.0, Education 4.0, Big Data, Machine Learning, Descriptive, Predictive and Prescriptive analysis as well as learning analytics tools to provide a guidance for the stakeholders of the Education Industry to enrich their process for getting improved student performances at risk.

The prediction of student performance helps the teaching learning process identify the direction of student progression and take remedial measures to step up the performance of weak students before it is too late. Additionally it also assists in identifying students with great potential and cater to their intellectual needs. This works as a feedback mechanism as well as feed forward mechanism. The feedback mechanism. It is also useful as feedback mechanism in apprising guardians of student progression and as feed forward approach for improving student result. It enables effective and intelligent data mining of student result data to forecast their potential performance. The paper presents an adaptive neuro fuzzy inference system with back propagation for prediction of student performance progression based on trends of past performances. The model is developed MATLAB R2018a software and validated by real time data set comprising of results of mix of students of various higher education institutions under an Indian state university. The model has a huge scope for quality management of teaching learning process in higher education.

In the ever-changing world of higher education services, examining factors that impact students’ performance is important in making sure that student’s learning experience can be improved to reach academic success. This research investigates the impact of University Servicescape (USc) and Information Systems Implementation Quality (ISQ) on student performance in higher education institutions in Malang. USc refers to the physical environment and facilities provided by the university. At the same time, the ISQ pertains to the effectiveness and efficiency of the technological systems employed for academic and administrative purposes. Both factors have been deeply researched separately in the context of higher education service management, but no research has delved into both at the same time. A quantitative empirical survey-based study is employed to examine this topic. The sample consists of university students studying in Malang, East Java, Indonesia. The results empirically show that USc and ISQ significantly impact university student performance in higher education, particularly within institutions in Malang, East Java, Indonesia. These findings should be useful for policymakers, university administrators, and educators in enhancing the delivery of educational services in higher education institutions across Indonesia

In this work, we focus on predicting student performance using educational data. Students have to choose elective and voluntary courses for successful graduation. Searching for suitable and interesting courses is time-consuming and the main aim is to recommend students such courses. Two beneficial approaches are thoroughly discussed in this paper. The results were achieved by analysis of study-related data and structural attributes computed from the social network. To validate the proposed method based on data mining and social network analysis, we evaluate data extracted from the information system of Masaryk University. However, the method is quite general and can be used at other universities.

This research presents a study and review of previous research. It demonstrates the use of the most important techniques in predictive analytics and machine learning algorithms to analyze historical data and accurately predict future outcomes of student performance. This research focuses on specific objectives, including techniques used to identify students at risk of poor academic performance or dropout and enable timely interventions to improve outcomes. Moreover, in this paper, the answers to questions, such as their benefits and limitations. By using data from sources such as academic records, attendance, and engagement metrics, educational institutions can uncover patterns in student behavior and performance. The research also presents the most important findings that were reached. The results show that predictive analytics not only improves individual student performance but also enhances the effectiveness of the institution by promoting a supportive and proactive learning environment. This approach provides educators and educational institutions with actionable insights to effectively enhance student retention and enhance academic achievement.

The dynamic landscape of higher education necessitates innovative approaches to enhance academic success and student performance. Traditional methods of evaluating and supporting student achievement frequently fall short in addressing the diverse and evolving needs of modern learners. This research explores the application of machine learning (ML) to predict student performance in higher education, aiming to develop a predictive model that can identify at-risk students early and enable targeted interventions. The study analyzes various factors influencing student performance, including demographic information, academic history, behavioral data, and socio-economic status. The proposed model demonstrates a high degree of accuracy, with an accuracy rate of 98.8%, a mean absolute error (MAE) of 0.402, and a root mean square error (RMSE) of 0.202. These metrics underscore the model's precision and reliability in predicting student outcomes. The significance of this research lies in its potential to transform educational practices by providing a data-driven framework for decision-making. Accurate predictions of student performance enable educational institutions to allocate resources more effectively, enhance student engagement, and ultimately improve graduation rates. Furthermore, this study contributes to the growing body of knowledge in educational data mining and learning analytics, offering insights that can be generalized across different educational contexts. This research aims to demonstrate the efficacy of machine learning in enhancing academic success and to provide a roadmap for future studies in this domain.

Predicting classifiers can be used to analyze data in K-12 education. Creating a classification model to accurately identify factors affecting student performance can be challenging. Much research has been conducted to predict student performance in higher education, but there is limited research in using data science to predict student performance in K-12 education. Predictive models are developed and examined in this review to analyze a K-12 education dataset. Three classifiers are used to develop these predictive models, including linear regression, decision tree, and Naive Bayes techniques. The Naive Bayes techniques showed the highest accuracy when predicting SAT Math scores for high school students. The results from this review of current research and the models presented in this paper can be used by stakeholders of K-12 education to make predictions of student performance and be able to implement intervention strategies for students in a timely manner.