Predictors Of Academic Performance Research Articles

Comparison between Multiple Linear Regression Models Vs Supervised Artificial Neural Networks in the Prediction of Ecuadorian Ser Bachiller 2018-2019 Grades

The article deals with the comparison between Multiple Linear Regression models vs supervised Artificial Neural Networks in the prediction of academic performance in the form of grades of the Ser-Bachiller evaluation of Ecuador, period 2018-2019. This by testing assumptions and calculating adequacy measures to identify the best prediction method. To meet the objective, information from the results of the Ser-Bachiller tests of Ecuador in the 2018-2019 cycle whose database is located on the official website of the National Institute of Educational Evaluation was used. There were 514852 students evaluated from all over the country. With this information we compared models that predict the scores in the domains of Mathematics, Linguistics, Science and Social Sciences, through factors associated with academic performance of Institutional, Pedagogical, Psychosocial and sociodemographic type.

An Effectual Model for Early Prediction of Academic Perfomance using Ensemble Classification

In the past few years, researchers are focused towards educational data mining (EDM) to improve the quality of education. Student’s academic performance prediction is a vital issue for improving the value of education. Research study conducted in the literature review mainly captivated the academic performance prediction at higher education. Though the academic performance at secondary level is infrequent, the same could be a scale for a student's performance at subsequent levels of education. Poor grades at lower levels also impact student’s future performance. In this paper, an effectual model is built with the help of significant factors that affect a student's academic performance at secondary level using single and ensemble techniques of classificification For this, both single and ensemble classification techniques are used in this paper To do the same, three single classifiers (classification algorithm) i.e., MLP, Random Forest and PART along with three well recognized ensemble algorithms Bagging (BAG), LogitBoost (LB) and Voting (VT) are applied on the datasets. For better performance of aforementioned classifiers, blended versions (single + ensemble-based classifiers) of classification models are also built. Assessment metrics i.e., accuracy, precision, recall and F-measure used to evaluate the performance of our proposed model. Evaluation results shows that Logitboost with Random Forest outperformed with 99.8% accuracy. It is clearly visible from results that the proposed model is useful for academic performance prediction to improve learning outcomes in future.

An Effectual Model for Early Prediction of Academic Perfomance using Ensemble Classification

In the past few years, researchers are focused towards educational data mining (EDM) to improve the quality of education. Student’s academic performance prediction is a vital issue for improving the value of education. Research study conducted in the literature review mainly captivated the academic performance prediction at higher education. Though the academic performance at secondary level is infrequent, the same could be a scale for a student's performance at subsequent levels of education. Poor grades at lower levels also impact student’s future performance. In this paper, an effectual model is built with the help of significant factors that affect a student's academic performance at secondary level using single and ensemble techniques of classificification For this, both single and ensemble classification techniques are used in this paper To do the same, three single classifiers (classification algorithm) i.e., MLP, Random Forest and PART along with three well recognized ensemble algorithms Bagging (BAG), LogitBoost (LB) and Voting (VT) are applied on the datasets. For better performance of aforementioned classifiers, blended versions (single + ensemble-based classifiers) of classification models are also built. Assessment metrics i.e., accuracy, precision, recall and F-measure used to evaluate the performance of our proposed model. Evaluation results shows that Logitboost with Random Forest outperformed with 99.8% accuracy. It is clearly visible from results that the proposed model is useful for academic performance prediction to improve learning outcomes in future.

Parental Engagement as a Predictor of Academic Performance among Secondary School Learners in Sheema District, Uganda

Purpose: Globally, parents' engagement in their children's education has been found to result in improved academic success. This study investigated the prediction effect of parental engagement on students’ academic performance in government grant-aided secondary schools in Sheema District, South Western Uganda.
 Methodology: The study used quantitative approach employing cross-sectional survey design. Participants included senior four students, parents of senior four students, and teachers teaching in senior four class. The participants were selected using simple random sampling technique. Data on parental engagement and learners’ academic performance were collected using a 5-point Likert scale questionnaire.
 Findings: Study results indicated a statistically significant effect of parental engagement in provision of basic needs (t = 5.242, p< .05), academic communication (t = 6.116, p< .05), decision making (t = 5.834, p< .05), infrastructural development and maintenance at school (t = 5.525, p< .05), provision of conducive learning environment (t = 6.819, p< .05), provision of adequate learning resources (t = 6.167, p< .05) on learners’ academic performance. However, the combined effects of parental engagement aspects did not significantly predict learners’ academic performance. The results imply that parental engagement in learners’ educational pursuit should be encouraged so as to enhance learners’ academic performance.
 Recommendation: It is therefore recommended that school programmes that can compel parents to participate in educational activities should be deliberately instituted so as to enhance academic performance among learners.

Emotion Regulation as Predictor of Academic Performance in University Students

The current study intended to examine the association between emotion regulation (i.e., cognitive reappraisal and expressive suppression) and academic performance in university students. In this correlational study, a sample of 300 (men=119; women=181) university students (BS and MS programs) in the age range of 18-29 years (M=21.45; SD=2.14) was selected randomly from a public sector university in Faisalabad city, Pakistan. The Emotion Regulation Questionnaire (Gross & John, 2003) was used to assess emotion regulation whereas the percentages of obtained marks in the last semester/degree program served as the measure of the academic performance of the participants. The results depicted a significant correlation between emotion regulation and academic performance indicating a significant positive association between cognitive reappraisal and academic performance while, a significant negative association between expressive suppression and academic performance in university students. Moreover, cognitive reappraisal and expressive suppression were found to be significant predictors of academic performance. Besides the significant implications of this study highlighting the role of relevant policymakers, university authorities, students’ counselors, and mental health professionals, suggestions for future studies are discussed based on the current findings.

Prediction of Final Academic Performance of Secondary School Students Based on Alcohol Consumptions and Diverse Backgrounds

The power of machine learning is prompting more educators to consider applying the technology to education. Also, alcoholism among students has become an important problem in society. Based on data from two US secondary schools, this paper investigates the impact of attributes including alcohol consumption, on students grades, and aims to predict students' final grades in Portuguese. The normal distribution index was used as a reference to analyze and clean the data. The visualization of the data to explore which attributes were most correlated with final grade has been achieved. In this paper, ridge regressor, decision tree regressor, decision tree classifier, and KNN classifier were used as training models, with MSE, MAE, r2, and accuracy as testing indexes and cross validation to verify results. The final results show that alcohol consumption has a significant negative impact on students' academic performance.

Prediction of Academic Performance of Students in Online Live Classroom Interactions—An Analysis Using Natural Language Processing and Deep Learning Methods

Prediction of Academic Performance of Students in Online Live Classroom Interactions—An Analysis Using Natural Language Processing and Deep Learning Methods

A Machine Learning Approach to Predicting Academic Performance in Pennsylvania’s Schools

Academic performance prediction is an indispensable task for policymakers. Academic performance is frequently examined using classical statistical software, which can be used to detect logical connections between socioeconomic status and academic performance. These connections, whose accuracy depends on researchers’ experience, determine prediction accuracy. To eliminate the effects of logical relationships on such accuracy, this research used ‘black box’ machine learning models extended with education and socioeconomic data on Pennsylvania to predict academic performance in the state. The decision tree, random forest, logistic regression, support vector machine, and neural network achieved testing accuracies of 48%, 54%, 50%, 51%, and 60%, respectively. The neural network model can be used by policymakers to forecast academic performance, which in turn can aid in the formulation of various policies, such as those regarding funding and teacher selection. Finally, this study demonstrated the feasibility of machine learning as an auxiliary educational decision-making tool for use in the future.

Enhanced Machine Learning model for Student Academic Performance Prediction using Genetic algorithm and compare with CNN model

Enhanced Machine Learning model for Student Academic Performance Prediction using Genetic algorithm and compare with CNN model

Predictors of academic performance of distance e-learners in a Nigerian University

This study was designed to analyze the predictors of the academic performance of distance e-learners. The population consisted of all distance learners in the university study centers in the South-West geopolitical zone. The sample of the study was made up of 1025 respondents from the university, which were selected using a purposive sampling technique. A mixed-method approach was used for the collection of data. This study applied ordinal regression analysis in searching for the best predictors among the variables under investigation in predicting the academic performance of distance e-learners. A quantitative approach was used to determine the best predictors. In contrast, a qualitative approach was used to support the quantitative results and reveal other variables not covered in the questionnaire. Results showed that five variables best predicted academic performance, and together they explained 10% of the variance in academic performance after considering all the rules that guide ordinal regression analysis. Frequency of engagement with information and communication technology (ICT) was found to be the strongest predictor, followed by students’ ICT literacy levels, marital status, previous academic performance and entry qualification. Based on the study's findings, it was recommended that policymakers and educational stakeholders fully support the implementation of e-learning in Nigerian universities.

Academic Performance in Transition to Online Distance Learning: An Assessment from Prior Academic Performance Across Subjects

Online distance learning (ODL) has spread worldwide in all levels of education, and academic performance is a frequently mentioned topic in the research of ODL. This research focuses on the impact of students’ prior academic performance in different subjects on their academic performance in the context of transition from a traditional class to online distance learning. The participants are students from a key public high school in China. They took a traditional in-person class in their twelfth grade first semester and took ODL in twelfth grade second semester. Positive and strong Spearman and Pearson Correlation (~0.8) is found between student’s academic performance during traditional class and student’s academic performance during ODL; positive and weak Spearman and Pearson Correlation (~0.4) is found between student’s academic performance during traditional class and the change of student’s academic performance through the transition from the traditional class to ODL, indicating a positive correlation between prior academic achievement and later performance. Linear regression fitting is applied to the student’s academic performance during traditional class and the student’s academic performance during ODL, the results have shown that the prior academic performance represents by cumulative exam have a good prediction of the later academic performance in both traditional class and ODL context.

Stressors and learned resourcefulness in baccalaureate nursing students: alongitudinal study.

This correlational longitudinal study examined levels and relationships of Learned Resourcefulness (LR), stressors, and academic performance in baccalaureate nursing students at a North Carolina university. Gadzella's Student-life Stress Inventory (SSI) and Rosenbaum's Self-Control Scale (SCS) administered to 85 students in two groups upon admission and graduation. LR increased, while stress decreased significantly in both groups (p < 0.05). Both groups (95.3% female, 85.8% Caucasian) reported similarly high frustration, pressure, and emotional reactions to stress. Significant relationship between taking tests and stress (p < 0.01). Stressors (p < 0.05) and age (p < 0.01) significant predictors of academic performance. Significant correlations of LR and work status (p < 0.01), and increased self-esteem (p<0.05). No significant relationships among LR, stressors, and academic performance. Results validate high levels of stress and suggest that higher LR enhances coping skills and decreases stress longitudinally, which can improve academic performance and retention. Trends and relationships in stressors and LR should be explored internationally in larger, more diverse samples of college students in nursing and other majors in relation to depression, anxiety, health-related behaviors, demographics, and academic performance. LR can be assessed, taught, learned, and enhanced. Greater numbers of qualified, competent nursing graduates with stronger clinical judgment, coping, and problem-solving skills will address the critical global nursing shortage and improve the quality, safety, and access of health care worldwide.

Academic performance prediction associated with synchronous online interactive learning behaviors based on the machine learning approach

ABSTRACT With long-term impact of COVID-19 on education, online interactive live courses have been an effective method to keep learning and teaching from being interrupted, attracting more and more attention due to their synchronous and real-time interaction. However, there is no suitable method for predicting academic performance for students participating in online class. Five machine learning models are employed to predict academic performance of an engineering mechanics course, taking online learning behaviors, comprehensive performance as input and final exam scores (FESs) as output. The analysis shows the gradient boosting regression model achieves the best performance with the highest correlation coefficient (0.7558), and the lowest RMSE (9.3595). Intellectual education score (IES) is the most important factor of comprehensive performance while the number of completed assignment (NOCA), the live viewing rate (LVR) and the replay viewing rate (RVR) of online learning behaviors are the most important factors influencing FESs. Students with higher IES are more likely to achieve better academic performance, and students with lower IES but higher NOCA tend to perform better. Our study can provide effective evidences for teachers to adjust teaching strategies and provide precise assistance for students at risk of academic failure in advance.

Predictive Modeling in Higher Education: Determining Factors of Academic Performance

For several decades in the field of data mining in education (EDM), predictive learning has remained one of the most popular and internationally discussed research topics. Specifically, data mining is used to predict educational outcomes such as academic performance, retention, success, satisfaction, achievement and dropout rates. In the management practice of higher education institutions, on the basis of an operational forecast, measures are developed and implemented to support those students who fall into the risk group.Our study is aimed at substantiating a model for predicting the early departure of students using an artificial neural network and analyzing predictors that increase the accuracy of predicting successful graduation from a Russian university. This work will expand the international practice of comparative research in higher education.The paper confirms the already existing hypotheses about the influence of a number of factors on the prediction of academic performance and suggests the need to test their universality or specificity in a particular institution of higher education. We also proved that an artificial neural network model with a certain set of attributes can be applied in the context of a single higher education institution, regardless of specialization. To determine the potential risk group of students, a binary classification prediction model is used. The overall prediction accuracy of a neural network with combined data reaches 88%. For this neural network model, the basic predictors that affect the accuracy of the forecast are the cumulative average level of achievement (CGPA) and the year of admission to the university.

Prediction of student academic performance based on their emotional wellbeing and interaction on various e-learning platforms

Prediction of student academic performance based on their emotional wellbeing and interaction on various e-learning platforms

ProbSAP: A comprehensive and high-performance system for student academic performance prediction

The student academic performance prediction is becoming an indispensable service in the computer supported intelligent education system. But conventional machine learning-based methods can only exploit the sparse discriminative features of student behaviors in imbalanced academic datasets to predict student academic performance (SAP). Furthermore, there is a lack of imbalanced data processing mechanisms that can efficiently capture student characteristics and achievement. Therefore, we propose a comprehensive and high-performance prediction framework to probe SAP characteristics (ProbSAP) on massive educational data, which can resolve imbalanced data issue and improve academic prediction performance for making course final mark prediction. It consists of three main components: collaborative data processing module for enhancing the data quality, scalable metadata clustering module for alleviating the imbalance of academic features, and XGBoost-enhanced SAP prediction module for academic performance forecasting. The collaborative data processing module integrates multi-dimensional academic data, which sustains a good supply for clustering and modeling in the ProbSAP framework. The comparative evaluation results demonstrate that ProbSAP delivers superior accuracy and efficiency improvement for the course final mark prediction of college students over other state-of-the-art methods such as CNN, SVR, RFR, XGBoost, Catboost-SHAP, and AS-SAN. On average, ProbSAP reduces the mean absolute error (MAE) by 84.76%, 72.11%, and 66.49% compared with XGBoost, Catboost-SHAP, and AS-SAN, respectively. It also leads to a better out-sample fit that minimizes prediction errors between 1% and 9% with over 98% of actual samples.

ADHD symptoms and maladaptive achievement strategies: the reciprocal prediction of academic performance beyond the transition to middle school

ABSTRACT This longitudinal study examined how two externalising behaviour problems, attention-deficit hyperactivity disorder (ADHD) and conduct disorder (CDs), are associated over time with low motivation (MAS), and how these problems effect academic performance. In our cross-lagged analysis, we found reciprocal effects between ADHD symptoms and MAS between Grades 5 and 6. Both domains also negatively predicted later academic performance. With CDs and MAS, no cross-lagged effects were found, although both were correlated and very stable over time, and negatively predicted later academic performance. These different kinds of externalising problem behaviours seem to differ in the way in which they interact with students’ MAS and academic performance in the long term. Students with ADHD symptoms are likely to be more vulnerable to negative learning experiences and the development of MAS than students with CDs.

Who succeeds in a leadership course? Achievement is predicted by ability-tested but not self-reported emotional intelligence

We examine Emotional Intelligence (EI) as a predictor of academic performance in business school leadership coursework. Leadership requires competent interaction with subordinates on an interpersonal level. This requires interpersonal skills, such as engaging in difficult conversations. We argue that performance in a course that develops these skills is facilitated by EI. We report data from two studies (Study 1 N = 609; Study 2 N = 529) in which students completed a battery of both self-reported and ability-tested EI measures. Controlling for cognitive ability and personality, ability-tested EI predicted leadership course grades in both studies, whereas self-reported EI did not do so in either. Each of the ability EI constructs tested—namely emotion perception, emotional understanding, emotion management, and emotion attention regulation—significantly predicted course performance. These findings suggest information about ability EI can lead to understanding who stands to benefit most from leadership education and for students to be more accurate in their self-assessments about their emotional abilities.

English Proficiency as a Predictor of Academic Performance in the Context of Non-English as a Medium of Instruction

English Proficiency as a Predictor of Academic Performance in the Context of Non-English as a Medium of Instruction

An Enhanced Student Engagement and Academic Performance Predictive System

Student engagement is one of the important constructs that is used to understand the behavior of the student towards the teaching-learning process, and it determines the students’ academic performance. The aim of this study is for predictive analytics to work on the comprehension of student commitment and scholarly execution and anticipate students who are in danger of low execution or commitment right on time before the evaluation to work with conceivable mediation to further develop the learning results in advanced education. This research adopts the process of machine learning such as linear regression, decision tree, naïve Bayes, KNN, Kmeans in order to identify the most effective determinants for student academic performance prediction. The result of this study shows that after testing the five attributes, we discovered so far that the attributes that has impact on student evaluation are their Race/Ethnicity and Parental level of Education. Thus, the early prediction of student performance can trigger educators to track student dropouts in a particular course at an early stage. The model can also be used as an early warning system to identify failure students in the classroom by the course coordinators and educators, to take strategic decisions to improve student performance.