Explore the vast range of titles available.

Predicting students’ performance is one of the most important topics for learning contexts such as schools and universities, since it helps to design effective mechanisms that improve academic results and avoid dropout, among other things. These are benefited by the automation of many processes involved in usual students’ activities which handle massive volumes of data collected from software tools for technology-enhanced learning. Thus, analyzing and processing these data carefully can give us useful information about the students’ knowledge and the relationship between them and the academic tasks. This information is the source that feeds promising algorithms and methods able to predict students’ performance. In this study, almost 70 papers were analyzed to show different modern techniques widely applied for predicting students’ performance, together with the objectives they must reach in this field. These techniques and methods, which pertain to the area of Artificial Intelligence, are mainly Machine Learning, Collaborative Filtering, Recommender Systems, and Artificial Neural Networks, among others.

In the world of student education is an important component where the role of students is as someone who is psychologically ready to receive lessons or other input from the school. However, each student has different performance and development, therefore it is important to do monitoring so that student performance will always be monitored by the school for improving student quality maintenance. Also, in the process of valuing education for students needs to be done by giving an appreciation in the form of giving gifts or just giving words and motivation so that students can perform better in learning and participating in other activities at school. In terms of selecting students with good performance or those who have a very declining development using the school method not only assess students by one criterion but with several criteria to produce a decision that can be accepted by many people. Performance Students must also be monitored by the school or the related rights. In this paper, the student performance prediction was assessed with 5 criteria components and the result shows there are 10 very satisfy students, 10 satisfying students, 10 well students, and 10 Enough students from sample 40 students.

Graduate students are unaware of their final qualification for a course. Even though there were many models available, few works with feature selection and prediction with no control over the number of features to be used. As a result of the lack of an improved performance forecasting system, students are only qualified on the second or third attempt. A warning system in place could help the students reduce their arrear count. All students undertaking higher education should obtain the qualification at their desired level of education without delay to transit to their careers on time. Therefore, there should be a predictive system for students to warn during the course work period and guide them to qualify in a first attempt itself. Although so many factors were present that affected the qualifying score, here proposed a feature selection technique that selects a minimal number of well-playing features. Also proposed a model Supervised Learning Approach to unfold Student's Academic Future Progression through Supervised Learning Approach for Student's Academic Future Progression (SLASAFP) algorithm that recommends the best fitting machine learning algorithm based on the features dynamically. It has proven with comparable predictive accuracy.

There is a high failure rate and low academic performance observed in programming courses. To address these issues, it is crucial to predict student performance at an early stage. This allows teachers to provide timely support and interventions to help students achieve their learning objectives. The prediction of student performance has gained significant attention, with researchers focusing on machine learning features and algorithms to improve predictions. This article proposes a model for predicting student performance in a 16-week CS1 programming course, specifically in weeks 3, 5, and 7. The model utilizes three key factors: grades, delivery time, and the number of attempts made by students in programming labs and an exam. Eight classification algorithms were employed to train and evaluate the model, with performance assessed using metrics such as accuracy, recall, F1 score, and AUC. In week 3, the gradient boosting classifier (GBC) achieved the best results with an F1 score of 86%, followed closely by the random forest classifier (RFC) with 83%. These findings demonstrate the potential of the proposed model in accurately predicting student performance.

Introductory Engineering Mathematics (a skill builder for engineers) involves developing problem-solving attributes throughout the teaching period. Therefore, the prediction of students’ final course grades with continuous assessment marks is a useful toolkit for degree program educators. Predictive models are practical tools used to evaluate the effectiveness of teaching as well as assessing the students’ progression and implementing interventions for the best learning outcomes. This study develops a novel multivariate adaptive regression spline (MARS) model to predict the weighted score WS (i.e., the course grade). To construct the proposed MARS model, Introductory Engineering Mathematics performance data over five years from the University of Southern Queensland, Australia, were used to design predictive models using input predictors of online quizzes, written assignments, and examination scores. About 60% of randomised predictor grade data were applied to train the model (with 25% of the training set used for validation) and 40% to test the model. Based on the cross-correlation of inputs vs. the WS, 12 distinct combinations with single (i.e., M1–M5) and multiple (M6–M12) features were created to assess the influence of each on the WS with results bench-marked via a decision tree regression (DTR), kernel ridge regression (KRR), and a k-nearest neighbour (KNN) model. The influence of each predictor on WS clearly showed that online quizzes provide the least contribution. However, the MARS model improved dramatically by including written assignments and examination scores. The research demonstrates the merits of the proposed MARS model in uncovering relationships among continuous learning variables, which also provides a distinct advantage to educators in developing early intervention and moderating their teaching by predicting the performance of students ahead of final outcome for a course. The findings and future application have significant practical implications in teaching and learning interventions or planning aimed to improve graduate outcomes in undergraduate engineering program cohorts.

The utilization of neural model techniques for predicting learner performance has exhibited success across various technical domains, including natural language processing. In recent times, researchers have progressively directed their attention towards employing these methods to contribute to socioeconomic sustainability, particularly in the context of forecasting student academic performance. Additionally, educational data frequently encompass numerous categorical variables, and the efficacy of prediction models becomes intricately tied to sustainable encoding techniques applied to manage and interpret this data. This approach aligns with the broader goal of fostering sustainable development in education, emphasizing responsible and equitable practices in leveraging advanced technologies for enhanced learning outcomes. Building on this insight, this paper presents a literature review that delves into the use of machine learning techniques for predicting learner outcomes in online training courses. The objective is to offer a summary of the most recent models designed for forecasting student performance, categorical coding methodologies, and the datasets employed. The research conducts experiments to assess the suggested models both against each other and in comparison to certain prediction techniques utilizing alternative machine learning algorithms concurrently. The findings suggest that employing the encoding technique for transforming categorical data enhances the effectiveness of deep learning architectures. Notably, when integrated with long short-term memory networks, this strategy yields exceptional results for the examined issue.

The aim of this paper is to examine students' performance in a computation-based course by evaluating the effects of key factors including sketching, visualization resources provided to them during the lectures, their attendance and tutors' experience. A systematic review was conducted including 192 articles published during January 2010 to December 2019. Further, a case study has been conducted in which 633 students from non-engineering backgrounds were taught a core course of construction over three-yearly sessions from 2017 to 2019. The performance has been assessed through two quizzes of 10% weight each, assignment of 40% weight and a final exam with 30% weight in 2017-18 and 40% weight in 2019 were utilized with an attendance criterion of below 75% as low attendance. The statistical result highlights that a clear difference of 14% overall marks exist between the students with less than 75% attendance and the ones with 75% and above in 2017 and a 10% gap in 2018. Students with high marks in sketching secured higher overall marks as compared to others highlighting that the sketching skill is useful to construction students. The findings contribute to the body of education knowledge by evaluating key influential factors and provide a useful benchmark to other educators in the field.

Educational institutions are creating a considerable amount of data regarding students, faculty and related organs. This data is an essential asset for academic institutions as it has valuable insights, knowledge and intelligence for the policymakers. Students are the fundamental entities and primary source of data creation in any educational environment. The educational institutions need to distinguish students who are weak in their studies and require special attention and monitoring to improve their learning behaviours, future academic performances and factors that can affect their interpretation. This paper adopted a hybrid classification model using Decision tree and support vector machine (SVM) algorithms to predict students’ academic performance. We statistically analyzed and identified factors that can affect students’ academic performance. The dataset used is collected from Bachelor students of the City University of Science and Information Technology (CUSIT). The experimental results revealed 71.79%, 74.04% and 78.85% for decision tree, and 69.87%, 74.04% and 71.15% accuracy for SVM models respectively for different splits. The study identified seven different factors that can directly affect the students’ performance associated with educational institutions and social networks. Factors like “time spent on social networks,” “type of games playing on mobiles,” and “time spent on playing mobile games” significantly affect students’ performance.

Abstract The use of data for governance purposes has been widely recognised as a way for national authorities to coordinate their activities across administrative levels and improve educational quality. This places the mid-central authority—in many countries the municipal level—in the midst of modern education governing. This article reports a case study analysis of the particular uses of performance data and numbers by mid-central municipal authorities in the daily work of governing schools in Norway. The three empirical case studies combine an analysis of policy document and fieldwork interviews with municipal administrators. The article contributes important insights into the role of municipal administrators as interpreters of policy goals at a crucial yet understudied level of the education system. In contrast to the dominant perspective in the data use literature, which often addresses implementation and the effectiveness of how numbers and data can be ideally designed and used, the results provide grounds for a more nuanced understanding of the institutional processes related to setting performance goals.

Modern approaches in education technology, which make use of advanced resources such as electronic books, infographics, and mobile applications, are progressing to improve education quality and learning levels, especially during the spread of the coronavirus, which resulted in the closure of schools, universities, and all educational facilities. To adapt to new developments, students’ performance must be tracked in order to closely monitor all unfavorable barriers that may affect their academic progress. Educational data mining (EDM) is one of the most popular methods for predicting a student’s performance. It helps monitoring and improving students’ results. Therefore, in the current study, a model has been developed so that students can be informed about the results of the computer networks course in the middle of the second semester and 11 machine algorithms (out of five classes). A questionnaire was used to determine the effectiveness of using infographics for teaching a computer networks course, as the results proved the effectiveness of infographics as a technique for teaching computer networks. The Moodle (Modular Object-Oriented Dynamic Learning Environment) educational platform was used to present the course because of its distinctive characteristics that allow interaction between the student and the teacher, especially during the COVID-19 pandemic. In addition, the different methods of classification in data mining were used to determine the best practices used to predict students’ performance using the weka program, where the results proved the effectiveness of the true positive direction of functions, multilayer perceptron, random forest trees, random tree and supplied test set, f-measure algorithms are the best ways to categories.