Predicting student final performance using artificial neural networks in online learning environments

<p class="MsoNormal" style="text-align: justify;"><span style="font-family: Times New Roman;">This paper explores machine learning approaches to predicting student performance using artificial neural networks. By employing educational data mining and predictive modeling techniques, accurate predictions of student outcomes were achieved. The results indicate that artificial neural networks exhibit high accuracy and reliability in forecasting student academic performance. Through comprehensive analysis and empirical testing, this approach significantly enhances the effectiveness of student performance predictions. Future research directions may include further optimization of the model's algorithms and expansion of the data sample size to improve prediction accuracy and applicability. The method demonstrated exceptional performance in predicting student outcomes, offering high accuracy and efficacy. By mining and analyzing extensive educational data, a predictive model was established and validated through experiments. We introduce a novel predictive model to the field of education, providing robust support for student learning and educational decision-making. Future enhancements can optimize the model, increase prediction precision, and expand application fields to better serve the development of educational endeavors.</span></p>

The prediction of student performance is a critical area in educational data mining, providing invaluable insights for early interventions and personalized learning strategies. This chapter explores the application of machine learning and deep learning algorithms in predicting academic success, focusing on the enhancement of traditional predictive models through advanced computational techniques. A comprehensive review of widely-used models such as decision trees, support vector machines, k-nearest neighbors, and random forests is presented, highlighting their strengths and limitations in handling educational data. In addition, the chapter delves into deep learning approaches, such as artificial neural networks, convolutional neural networks, recurrent neural networks, and long short-term memory networks, which have shown promising results in capturing complex patterns and temporal dependencies in student performance data. The chapter emphasizes the importance of high-quality data preprocessing, including data cleaning, feature selection, and imputation, as essential steps for enhancing model accuracy. Evaluation metrics such as accuracy, precision, recall, F1-score, and ROC-AUC curve analysis are discussed to ensure robust model validation, especially in the presence of class imbalance. Further, challenges like model overfitting and strategies to prevent it, including regularization, cross-validation, and early stopping, are explored. The integration of machine learning and deep learning in education holds transformative potential for improving academic outcomes, providing a framework for data-driven decisions and timely interventions. This chapter serves as a critical resource for researchers and practitioners aiming to leverage AI for enhanced student performance prediction.

Aim/Purpose: This research aims to present a brand-new approach for student performance prediction using the Learning Fuzzy Cognitive Map (LFCM) approach. Background: Predicting student academic performance has long been an important research topic in many academic disciplines. Different mathematical models have been employed to predict student performance. Although the available sets of common prediction approaches, such as Artificial Neural Networks (ANN) and regression, work well with large datasets, they face challenges dealing with small sample sizes, limiting their practical applications in real practices. Methodology: Six distinct categories of performance antecedents are adopted here as course characteristics, LMS characteristics, student characteristics, student engagement, student support, and institutional factors, along with measurement items within each category. Furthermore, we assessed the student’s overall performance using three items of student satisfaction score, knowledge construction level, and student GPA. We have collected longitudinal data from 30 postgraduates in four subsequent semesters and analyzed data using the Learning Fuzzy Cognitive Map (LFCM) technique. Contribution: This research proposes a brand new approach, Learning Fuzzy Cognitive Map (LFCM), to predict student performance. Using this approach, we identified the most influential determinants of student performance, such as student engagement. Besides, this research depicts a model of interrelations among the student performance determinants. Findings: The results suggest that the model reasonably predicts the incoming sequence when there is a limited sample size. The results also reveal that students’ total online time and the regularity of learning interval in LMS have the largest effect on overall performance. The student engagement category also has the highest direct effect on student’s overall performance. Recommendations for Practitioners: Academic institutions can use the results and approach developed in this paper to identify students’ performance antecedents, predict the performance, and establish action plans to resolve the shortcomings in the long term. Instructors can adjust their learning methods based on the feedback from students in the short run on the operational level. Recommendation for Researchers: Researchers can use the proposed approach in this research to deal with the problems in other domains, such as using LMS for organizational/institutional education. Besides, they can focus on specific dimensions of the proposed model, such as exploring ways to boost student engagement in the learning process. Impact on Society: Our results revealed that students are at the center of the learning process. The degree to which they are dedicated to learning is the most crucial determinant of the learning outcome. Therefore, learners should consider this finding in order the gain value from the learning process. Future Research: As a potential for future works, the proposed approach could be used in other contexts to test its applicability. Future studies could also improve the performance level of the proposed LFMC model by tuning the model’s elements.

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 student performance using e-mail assessments can help in early interventions to better assist students sooner, rather than later, in STEM courses. In this paper, we propose CorC-Net, a tiny artificial neural network (ANN) that operates on limited data comprised of features scored from student assessments based on writing e-mails. ANNs are typically built using large scale data sets to truly realize their full potential; however, tiny neural networks overcome this problem by utilizing smaller batches of data making them easier to train. COrC-Net uses scored e-mails for content, organization, and clarity and classifies how students will perform. Formative instructor feedback provided between the assessments implies that CorC-Net is a more logical fit to simulate the “learning” process when human reaction to feedback and corrective action is involved. This is true especially in sequential course assessment tasks. In this paper, we show that COrC-Net outperforms other multiclass classification algorithms like decision trees, support vector machines, Gaussian Naive Bayes, and K-nearest neighbors. CorC-Net's success in classifying student performance shows great potential in courses where longterm temporal assessment data is not available.

Student performance modelling is one of the challenging and popular research topics in educational data mining (EDM). Multiple factors influence the performance in non-linear ways; thus making this field more attractive to the researchers. The widespread availability of e ducational datasets further catalyse this interestingness, especially in online learning. Although several EDM surveys are available in the literature, we could find only a few specific surveys on student performance analysis and prediction. These specific surveys are limited in nature and primarily focus on studies that try to identify possible predictor or model student performance. However, the previous works do not address the temporal aspect of prediction. Moreover, we could not find any such specific survey which focuses only on classroom-based education. In this paper, we present a systematic review of EDM studies on student performance in classroom learning. It focuses on identifying the predictors, methods used for such identification, time and aim of prediction. It is significantly the first systematic survey of EDM studies that consider only classroom learning and focuses on the temporal aspect as well. This paper presents a review of 140 studies in this area. The meta-analysis indicates that the researchers achieve significant prediction efficiency during the tenure of the course. However, performance prediction before course commencement needs special attention.

Educational data mining (EDM) is a strategic technique for exploring data in educational environments to gain a deeper understanding of education. One of the goals of EDM is to predict things related to students in the future which can be done using a machine learning approach. In this paper, a regression model is developed to predict student performance in the first semester and the waiting period for graduate employment using machine learning approach based on informatics management (MI) and non-informatics management (non-MI) student data. Four regression models are compared for predicting student performance in the first semester and waiting period for graduate employment, including support vector regression (SVR), random forest regression (RFR), AdaBoost regression (ABR), and XGBoost regression. Based on the experiment, prediction of students' performance in the first semester, the highest R2 result produced by SVR model by value of 0.58 for MI and by RFR by value of 0.34 for non-MI. While, waiting period for graduate employment prediction, the highest R2 result produced by AdaBoost regression by value of 0.44 for MI and SVR by value of 0.39 for non-MI.

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

Udder measures have been used to assess milk yield of sheep through classical methods of estimation. Artificial neural networks (ANN) can deal with complex non-linear relationships between input and output variables. In the current study, ANN were applied to udder measures from Pelibuey ewes to estimate their milk yield and this was compared with linear regression. A total of 357 milk yield records with its corresponding udder measures were used. A supervised learning was used to train and teach the network using a two-layer ANN with seven hidden structures. The globally convergent algorithm based on the resilient backpropagation was used to calculate ANN. Goodness of fit was evaluated using the mean square prediction error (MSPE), root MSPE (RMSPE), correlation coefficient (r), Bayesian’s Information Criterion (BIC), Akaike’s Information Criterion (AIC) and accuracy. The 15–15 ANN architecture showed that the best predictive milk yield performance achieved an accuracy of 97.9% and the highest values of r2 (0.93), and the lowest values of MSPE (0.0023), RMSPE (0.04), AIC (− 2088.81) and BIC (− 2069.56). The study revealed that ANN is a powerful tool to estimate milk yield when udder measures are used as input variables and showed better goodness of fit in comparison with classical regression methods.

Vocational education increasingly adopts blended learning approaches, combining online and traditional instruction to enhance skill development and learning outcomes. As students engage in various digital activities, they generate large volumes of behavioral data that can be leveraged to predict academic performance and enable early intervention for at-risk learners. This research proposes a deep learning-based student performance prediction framework tailored to vocational education environments, utilizing multi-source behavioral data. Data were collected from 2000 vocational learners enrolled in a semester-long program. The framework utilizes multi-source behavioral data, including Learning Management System (LMS) activity logs, internet usage patterns, attendance records, assessments, and demographic information, to enhance predictive accuracy and support early intervention in vocational education. Data were preprocessed by handling missing values, data cleaning, and min-max normalization. Principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) were fused to extract dynamic behavioral features. The proposed model, the Seven-spot Ladybird Optimized Multi-Source Attention-based Gated Recurrent Units (SLO-MSAGRU) model, is applied to predict student performance in vocational education. Implemented in Python, the findings show that the SLO-MSAGRU approach performs better than multimodal baseline architectures, achieving superior results with accuracy, F1-score, recall, and precision ranging from 95% to 98%. These findings reveal that broader internet behavior patterns contribute more significantly to student performance prediction than platform-specific learning data. The framework offers a practical tool for educators to apply personalized learning strategies and timely interventions, thereby improving decision-making in vocational training environments.

Objectives: Data mining techniques are implemented in many organizations as a standard procedure for analyzing the large volume of available data, extracting useful information and knowledge to support the major decision-making processes. Data mining can be applied to wide variety of applications in the educational sector for the purpose of improving the performance of students as well as the status of the educational institutions. Educational data mining is rapidly developing as a key technique in the analysis of data generated in the educational domain. Methods: The aim of this study presents an analysis of final year results of UG degree students using data mining technique, which carried out in three of the private colleges in Tamil Nadu state of India. The primary objective of this research work is to apply the classification techniques to the prediction of the performance of students in end semester university examinations. Particularly, the decision tree algorithm C4.5 (J48), Bayesian classifiers, k Nearest Neighbor algorithm and two rule learner’s algorithms namely OneR and JRip are used for classifying the performance of students as well as to develop a model of student performance predictors. Results: The result of this study reveals that overall accuracy of the tested classifiers is above 60%. In addition classification accuracy for the different classes reveals that the predictions are worst for distinction class and fairly good for the first class. The JRip produces highest classification accuracy for the Distinction. Classification of the students based on the attributes reveals that prediction rates are not uniform among the classification algorithms. Also shows that selected data attributes have found to be influenced the classification process. The results showed to be satisfactory. Improvements: The study can be extended to draw the performance of other classification techniques on an expanded data set with more distinct attributes to get more accurate results.

Current literature outlines the documented need for improved communication during patient medication counseling. Although many tools exist, there needs to be a national standardized tool that complies with federal and state law, to objectively measure student pharmacist performance during patient counseling in the community pharmacy setting. The primary objective of this study is to perform an initial analysis of the internal consistency reliability of a patient medication counseling rubric designed with an Indian Health Services theoretical framework. Secondary objectives include measuring changes in student performance over the time of the study. The 18-item rubric was developed to objectively measure student pharmacist performance during patient medication counseling sessions in a 21-h Introductory Pharmacy Practice Experience (IPPE) course. The community-pharmacy-based IPPE patient counseling course evaluates students' communication skills and patient-centered counseling techniques in live and simulated patient counseling sessions. Three pharmacist evaluators assessed a total of 247 student counseling sessions. The rubric's internal consistency reliability was analyzed, and student performance improvement was observed within the course. Students' performance was evaluated as “meets expectations” in most live and simulated sessions. However, an independent groups t-test showed that the mean performance score for the live counseling sessions (2.59, SD = 0.29) was higher (p < 0.001) than that for the simulated counseling sessions (2.35, SD = 0.35). Students' performance in the course improved over three weeks [Week 1: mean (SD) = 2.29 (0.32), Week 2: mean (SD) = 2.44 (0.33), Week 3: mean (SD) = 2.62 (0.29); p < 0.001]. A Tukey-Kramer comparison post hoc test found a significant increase in the mean performance scores between weeks (p < 0.05). The overall internal consistency reliability of the counseling rubric was determined acceptable, with a Cronbach's alpha of 0.75. Further study is required, including the assessment of inter-rater reliability, factor analysis, variable analysis, and use in other states with patient confirmation testing necessary to validate the rubric for use with student pharmacists in the community pharmacy setting.

A significant amount of research works has tackled the problem of students’ performance prediction. The introduction of learning management systems enabled providing teachers and students with accurate predictions to take remedial actions, and enhance students’ achievement. This paper proposes a new students’ performance prediction model based on different academic and non-academic features. We use a filter-based feature selection model to select a subset of the features that can describe the input data and reduce feature space dimensionality. A subsequent classification algorithm classifies students’ feature vectors to predict student performance. The obtained results reveal a strong relationship between students’ behavioral features and academic achievement. Moreover, results indicated that a Random Forest classifier with 5-fold cross-validation outperforms other algorithms, including Support Vector Machine, K-nearest neighbor, and Artificial Neural Network. Applying a Random Forest classifier on the reduced number of features provide 83.33%, 82.8, and 83% for accuracy, precision, and recall, metrics, respectively.

The optimal performance of a hydroelectric power plant depends on accurate monitoring and well-functioning sensors for data acquisition. This study proposes the use of artificial neural networks (ANNs) to estimate the Pelton turbine shaft power of a 10 kW micro-hydropower plant. In the event of a failure of the sensor measuring the torque and/or rotational speed of the Pelton turbine shaft, the synthetic turbine shaft power data generated by the ANN will allow the turbine output power to be determined. The experimental data were obtained by varying the operating conditions of the micro-hydropower plant, including the variation of the input power to the electric generator and the variation of the injector opening. These changes consequently affected the flow rate and the pressure head at the turbine inlet. The use of artificial neural networks (ANNs) was deemed appropriate due to their ability to model complex relationships between input and output variables. The ANN structure comprised five input variables, fifteen neurons in a hidden layer and an output variable estimating the Pelton turbine power. During the training phase, algorithms such as Levenberg–Marquardt (L–M), Scaled Conjugate Gradient (SCG) and Bayesian were employed. The results indicated an error of 0.39% with L–M and 7% with SCG, with the latter under high-flow and -energy consumption conditions. This study demonstrates the effectiveness of artificial neural networks (ANNs) trained with the Levenberg–Marquardt (L–M) algorithm in estimating turbine shaft power. This contributes to improved performance and decision making in the event of a torque sensor failure.

The Brain Emotional Learning (BEL) is a novel bio-inspired machine learning approach mentioned as a new class of artificial neural network (ANN). The artificial emotional neural network (AENN) is one of the BEL methods which used the genetic algorithm (GA) to compute proper weights, weights of the amygdala (AMYG), orbitofrontal cortex (OFC) weights and a bias value. AENN trained by GA has been reported that it could produce low error rates. However, AENN still has more rooms to enhance its prediction of performance, especially generalization and the prediction of performance. Therefore, this paper aims to propose a new training method for AENN. The JAYA optimization algorithm optimized the weights and the biases of AENN. Two new proposed models are named as AENN-Max-JAYA and AENN-Mean-JAYA. Their names are according to the way of selecting the additional expanded feature which obtained through either the max or the average of input patterns, respectively. From the experimental results for wind power forecasting dataset, the proposed methods proved that the results are better in generalization performance and give lower error rates which compared to the comparative AENN models and traditional ANNs.