A Study on Predictive Modelling of Student Academic Performance using Machine Learning Method

The aim of this study is to undertake an empirical inquiry and comparison of the effectiveness of various classifiers with ensembles classifiers in the prediction of student academic performance. A single classifier algorithm will be compared against the performance and efficiency of ensemble classifiers. Reducing student attrition is a major problem for educational institutions all over the world. The search for solutions to increase student retention and graduation rates continues for educators. This is only possible if at-risk students are identified and intervened with as soon as possible. However, the majority of regularly used prediction models are inefficient and inaccurate as a result of inherent classifier limitations and the inclusion of insignificant inputs in their calculations. The majority of data mining and machine learning researcher focused on developing an algorithm that can extract useful information from massive amounts of data after being processed by a computer. The most difficult problem in predictive modelling is identifying the most effective prediction algorithms that are also accurate enough to be useful. Therefore, a multi-level homogeneous ensemble predictive (MLHoEP) model is designed, which uses the different techniques of data mining like feature selection, ensemble learning techniques like boosting and bagging. Seven distinct machine learning algorithms were used on this model to predict and analyse the academic performance of the students. The performance of the classification algorithms in terms of prediction was evaluated using k-fold cross-validation. The study contributes to the body of knowledge by suggesting the development of homogeneous classifiers that may be used to accurately predict students’ academic success. It also proposes the construction of homogeneous classifiers, which may be deployed for accurate student performance prediction, in order to provide a better explanation for the poor performance prediction. As a result of this research, it has been demonstrated that the technique of applying homogeneous ensemble approaches is incredibly efficient and accurate in terms of predicting student performance and assisting in identifying students, who are in danger of dropping out of school. The study compared the accuracy and efficiency of single classifiers to ensembles of classifiers in terms of performance. It was discovered in the research that a homogeneous model with excellent accuracy and efficiency might be developed for anticipating student performance. These key problems have been successfully addressed by the findings of this research study: Which characteristics of students are the most effective predictors of academic performance? How accurate are approaches such as bagging and boosting ensembles for predicting student academic performance? The approach offered in this study will aid educational administrators and policymakers in designing new policies and curriculum-linked to student retention in higher education. This research can also aid in the identification of students who are at risk of dropping out of school early, providing for timely intervention and support. Prospective research will examine the creation and implementation of an automated prediction system known as the students’ academic performance forecast framework, which will collect data from students via online submission and produce a prediction result for their academic performance.KeywordsEducational data miningEnsemble learningMultilayer perceptronRandom forestNaïve BayesCorrelation attribute evaluationInformation gainGain ratio

Effects of co-curricular activities on student's academic performance by machine learning

The research paper examines important aspects of using approaches to learning analytics (LA) and educational data mining (EDM), which can be used to develop educational programs and track progress. It has been shown that the integration of learning analytics into a learning management system (LMS) can improve the effectiveness of the educational process by predicting and preventing problems faced by students with regard to academic performance. The process of analyzing and predicting academic performance data using machine learning methods, including linear regression, with the determination of the ratio of academic performance in a discipline and GPA points is considered. The result of the study shows the importance of choosing the right functions to improve the accuracy of forecasting using machine learning models, and also provides input data to improve the educational program. The process of creating predictive models for assessing student academic performance by collecting and preparing data using machine learning algorithms is considered. A clear description of the use of models to predict the future academic performance of students is given, and special attention is paid to the interpretation of the results obtained to identify the main factors affecting academic performance. This work contributes to the development of the field of learning analytics and the fields of educational data production, offering practical recommendations for curriculum management and improving the quality of data-based education.

Student performance is related to complex and correlated factors. The implementation of a new advancement of technologies in educational displacement has unlimited potentials. One of these advances is the use of analytics and data mining to predict student academic accomplishment and performance. Given the existing literature, machine learning (ML) approaches such as Artificial Neural Networks (ANNs) can continuously be improved. This work examines and surveys the current literature regarding the ANN methods used in predicting students’ academic performance. This study also attempts to capture a pattern of the most used ANN techniques and algorithms. Of note, the articles reviewed mainly focused on higher education. The results indicated that ANN is always used in combination with data analysis and data mining methodologies, allowing studies to assess the effectiveness of their findings in evaluating academic achievement. No pattern was detected regarding selecting the input variables as they are mainly based on the context of the study and the availability of data. Moreover, the very limited tangible findings referred to the use of techniques in the actual context and target objective of improving student outcomes, performance, and achievement. An important recommendation of this work is to overcome the identified gap related to the only theoretical and limited application of the ANN in a real-life situation to help achieve the educational goals.

Predicting academic performance associated with physical fitness of primary school students using machine learning methods

PurposeCreating suitable learning conditions in university classrooms continues to be a topical issue in higher education. The above means that a continued search for innovative teaching and learning strategies in universities remains a priority issue. The study therefore investigated conditions that facilitate the effective implementation of cooperative learning (CL) as well as how CL influences the academic performance of students in universities in Zimbabwe.Design/methodology/approachThe research adopted a quantitative research approach located in the descriptive research design. A sample of 341 undergraduate students selected using a simple random sampling strategy from a sample frame of 701 undergraduate students participated in the study. The study first used a pre-test and later, a post-test to determine the initial and end of semester (EOS) academic performance levels of students, respectively, on a Calculus 1 course. A self-constructed structured questionnaire was also used for data collection on the views of students towards the use of CL with particular reference to the 5 dimensions of positive interdependence (PDI), promotive interaction (PI), individual and group accountability (IGA), social and interpersonal skills (SS) and group processing (GP). The questionnaire was validated using confirmatory factor analysis. Structural equation modelling was used to test proposed relationships. A total of 341 questionnaires were administered through an email survey. Of the total, 149 completed questionnaires were received from the students, giving a return rate of 43.7%.FindingsThe results showed that positive interdependence, promotive interaction, social and interpersonal skills, individual and group accountability as well as group processing were important antecedents to the effective implementation of CL in universities. The results further showed that CL plays a significant role in improving the academic performance of university students; hence, academic performance was viewed as a significant consequence of CL.Research limitations/implicationsThis is the first study on the application of CL to enhance the academic performance of university students in the context of Zimbabwe. As a result, caution should be exercised when generalising the results as more studies to either confirm or disconfirm these results in the context of Zimbabwe may still be required.Practical implicationsThese results have implications on policy and practice with regards to active teaching strategies in universities. With regards to practice, the results demonstrated that the use of group activities that allow students to share knowledge and support each other while the teacher plays a facilitating role is important for enhancing students' academic performance. With regards to policy, the results showed that universities can enhance the academic performance of students if policies that promote student-centered teaching and learning approaches to ensure that teaching in universities is more student-led than lecturer-led are developed.Originality/valueWhile many studies have been conducted in other contexts, to establish the influence of CL on the academic performance of university students, there is no known study on the influence of CL that has been conducted in the context of Zimbabwean universities. The results of this study therefore are an eye opener on the role of CL in enhancing the academic performance of students in Zimbabwean universities.

Accurate prediction of student academic performance plays a vital role in enabling early intervention, adaptive instruction, and data-driven educational decision-making. However, the effectiveness of deep learning models such as Long Short-Term Memory (LSTM) networks is often constrained by suboptimal hyper-parameter tuning and insufficient exploration of the search space. To overcome these limitations, this paper introduces a novel hybrid learning framework, CNAE-LSTM, which integrates Chaotic initialization, a Niche-based evolutionary mechanism, and Alpha Evolution (AE) into a unified optimization paradigm termed Chaotic Niche Alpha Evolution (CNAE). Specifically, a chaotic operator is first employed to enhance population diversity during initialization; then a niche-based grouping strategy partitions the population into three subgroups with distinct mutation probabilities to preserve diversity and avoid premature convergence; finally, an Alpha Evolution mechanism guides the evolutionary search toward promising regions with improved exploration–exploitation balance. The proposed CNAE is utilized to optimize key LSTM hyper-parameters, including network architecture and training settings. Extensive experiments conducted on a real-world secondary education dataset demonstrate that CNAE-LSTM consistently outperforms conventional LSTM, SVM, CNN, Transformer models, as well as LSTM enhanced by QGA, QPSO, CWOA, QGWO, and grid/random search strategies. Results show that CNAE-LSTM achieves superior predictive accuracy, stability, and generalization capability, validating the effectiveness of the proposed hybrid framework for improving academic performance prediction.

This study compares the effectiveness of virtual and traditional field trip strategies on academic performance and motivation of students in conservation concepts of biology in North-West Nigeria. The study developed 2 research objectives one of which is to: compare the effectiveness of virtual and traditional field trip strategies on academic performance of students in conservation concept. The study was guided by 2 research questions and 2 null hypotheses. A Quasi experimental research using test-retest method of pretest and posttest was adopted for the study. A sample of 120 N.C.E II biology students comprising of 81 males and 39 females were randomly selected from the population of 357 students of which 213 are males and 114 are females. The study developed 2 instruments namely: Conservation Concepts Performance Test (CCPT) and Conservation Concepts Motivation Questionnaire (CCMQ) which are validated and found reliable with r=0.65. At the end of the treatment data was collected and analyzed using Means and standard deviations to answer the research question while t-test and Mann- Whitney Statistics were used to answer the null hypotheses. The results obtained showed that: significant differences exist between the performance of students taught using virtual field trip strategy and those exposed to traditional field trip strategy. From the findings recommendations were made one of which is: the Ministry of Education/ colleges should provide a biology Virtual environment to serve each school in the region as technology is seen to help improve the performance and raise the level of motivation in biology concepts, moreover it will help to overcome problems faced by teachers from a lack of real field trips which leads to ignorance of some abstract concepts such as conservation concepts biology.

BackgroundThis study aimed to examine differences in socio-demographics and health behaviour between Belgian first year university students who attended all final course exams and those who did not. Secondly, this study aimed to identify weight and health behaviour related correlates of academic performance in those students who attended all course exams.MethodsAnthropometrics of 101 first year university students were measured at both the beginning of the first (T1) and second (T2) semester of the academic year. An on-line health behaviour questionnaire was filled out at T2. As a measure of academic performance student end-of-year Grade Point Averages (GPA) were obtained from the university’s registration office. Independent samples t-tests and chi 2 -tests were executed to compare students who attended all course exams during the first year of university and students who did not carry through. Uni- and multivariate linear regression analyses were conducted to identify correlates of academic performance in students who attended all course exams during the first year of university.ResultsStudents who did not attend all course exams were predominantly male, showed higher increases in waist circumference during the first semester and consumed more French fries than those who attended all final course exams. Being male, lower secondary school grades, increases in weight, Body Mass Index and waist circumference over the first semester, more gaming on weekdays, being on a diet, eating at the student restaurant more frequently, higher soda and French fries consumption, and higher frequency of alcohol use predicted lower GPA’s in first year university students. When controlled for each other, being on a diet and higher frequency of alcohol use remained significant in the multivariate regression model, with frequency of alcohol use being the strongest correlate of GPA.ConclusionsThis study, conducted in Belgian first year university students, showed that academic performance is associated with a wide range of weight and health related behaviours. Future studies should investigate whether interventions aiming at promoting healthy behaviours among students could also have a positive impact on academic performance.

Introduction: Educational Data Mining and Machine Learning Models gained more interest among researchers and academicians in recent years. These are used to extract meaningful data from the educational database can be applied to predict the student academic performance. Objective: The main objective of this research shows the capability to predict the student's performance and is highly beneficial to take remedial actions in the present educational system. It also offers suitable student assistance, allows an educational institution or teacher to help the students in gaining extra marks. Methods: The presented model operates in two stages, namely classification and outlier detection. Initially, a multilayer perceptron is employed for data classification. Later, a stochastic gradient descent classifier and multi-layer perceptron are integrated to effectively classify the data. For further improvement in the classification, Student academic performance, outlier detection method namely radial basis function is applied to remove the misclassified instances. Results: The proposed model achieves superior classification performance with the maximum precision of 79.30, recall of 79.30, and accuracy of 79.30, F-score of 79.30 and kappa value of 52.40 respectively. The simulation outcome exhibited that the multilayer perceptron and stochastic gradient descentmodel offers better results over the other classifiers. However, the usage of outlier detection using the radial basis function model takes the classifier results to the next level. Conclusion: Using classification techniques a new student academic performance model is proposed by addressing some issues in the existing model which is used to predict the student academic performance assist inproper time.

The aim of this research study is to find out cause and effect of clinical depression on academic achievements and performance of students. The Main objective of this chronic mental illness is to find out the striking depth of stress and depression on learning outcomes of students. Factors that impact on academic performance caused by clinical depression were investigated. Literature review indicates that clinical depression negatively impact on academic performance of students in terms of lack of confidence, communication problem, time management and trust issues particularly at university level. Public sector university of Karachi was selected as the population of the study. This research is based on the quantitative method. Questionnaire has been set, as a tool for this research. The sample size included 100 students from twenty departments of eight faculties through simple random sampling. Data analysis has been done by descriptive statistical techniques using percentage method. Closed ended questionnaire tool were designed for the collection of data based on five liker scale. The collected was analyzed and results were at moderate level 33% respondents were strongly agree, 47% agree, 13% neutral while strongly disagree and disagree were7%.The findings of this research shows that clinical depression adversely impact on academic performance of the students at University of Karachi. It affects academic performance as well as it has long term impact on student’s mental performance. The hypothesis considered for this research is accepted.

Education for centuries has focused on the intellect, leaving aside the emotional factor, which impacts the mental health of students and, in turn, academic performance. The objective is to establish the relationship between emotional intelligence with academic performance in university students. It is multicenter with a quantitative approach; sampling is non-probabilistic. The TMMS-24 meta-knowledge trait scale about emotional states was applied to measure Emotional Intelligence. In the academic performance, the general average of the participants was used. There is a relationship between levels of emotional intelligence with academic performance. The information is useful for proposing intervention strategies during the training of emotional competencies from admission.

Introduction Several studies in the literature have highlighted the impact of cognitive impairment and academic performance (AP) in students with sensorineural hearing loss in specialised schools for the deaf. However, few studies have been conducted on this subject in our setting. Purpose The objective of this study was to determine the influence of hearing impairment (HI) and cognitive level on AP in students attending specialised schools for the deaf in Kongo Central. Methods This was a cross-sectional study conducted among 126 deaf students. The parameters collected included sociodemographic, clinical, and paraclinical data. HI was confirmed using pure tone audiometry (PTA) and classified according to WHO criteria. Cognition was assessed using Raven’s Standard Progressive Matrices (SPM), a non-verbal intelligence test, to determine the intelligence quotient (IQ). Data were analysed using SPSS version 26.0. Results A total of 126 students, including 75 boys, were enrolled. The dominant age group was >18 years (44.4%). Most participants were Jehovah’s Witnesses (38.1%) and lived in low-income households (62.7%). Nearly 85.7% of the students had severe to profound HI, with post-lingual onset in 60.3%, and 57.1% had a low IQ. The mean AP was 50.54 ± 6.56%. There was a weak negative correlation between hearing loss and AP (r = -0.30; p < 0.001). Students with above-average IQ had significantly higher AP scores compared to those with low or average IQ (p = 0.005). A significant negative correlation was also observed between advancing age and IQ (p < 0.001), indicating that IQ tends to decline slightly with age, explaining 10.7% of the variance. Conclusion The lack of schooling for deaf children is a significant issue in our context. Advancing age significantly impairs AP, underscoring the need to enrol these students at the appropriate school age.

This study addresses fairness in machine learning for student academic performance prediction using the UCI Student Performance dataset. We comparatively evaluate logistic regression, Random Forest, and XGBoost, integrating the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance and 5-fold cross-validation for robust model training. A comprehensive fairness analysis is conducted, considering sensitive attributes such as gender, school type, and socioeconomic factors, including parental education (Medu and Fedu), cohabitation status (Pstatus), and family size (famsize). Using the AIF360 library, we compute the demographic parity difference (DP) and Equalized Odds Difference (EO) to assess model biases across diverse subgroups. Our results demonstrate that XGBoost achieves high predictive performance (accuracy: 0.789; F1 score: 0.803) while maintaining low bias for socioeconomic attributes, offering a balanced approach to fairness and performance. A sensitivity analysis of bias mitigation strategies further enhances the study, advancing equitable artificial intelligence in education by incorporating socially relevant factors.

Student academic performance prediction is important to improve education with insights into student behavior, learning, and academic achievement by schools. The day-to-day method is non-personalized, and as such, proper learning strategies are challenging to deliver. This work presents a machine learning system for predicting student performance, providing learning recommendations based on personality, and examining student interaction. With learning history, test scores, and personality information, While using machine learning algorithms like Random Forest, Support Vector Machine, Logistic Regression, and K-Nearest Neighbors to obtain the highest rate of prediction. This system goes beyond learning assistance by providing personalized learning recommendations and activity tracking in real-time. The findings of the research show that the method is more accurate than the conventional models, filling the gap between machine learning and adaptive learning. This project is designed to attain the optimal academic assistance and maximize the learning experience of the students.