Search

The tremendous growth of educational institutions' electronic data provides the opportunity to extract information that can be used to predict students' overall success, predict students' dropout rate, evaluate the performance of teachers and instructors, improve the learning material according to students' needs, and much more. This paper aims to review the latest trends in predicting students' performance in higher education. We provide a comprehensive background for understanding Educational Data Mining (EDM). We also explain the measures of determining academic success and highlight the strengths and weaknesses of the most common data mining (DM) tools and methods used nowadays. Moreover, we provide a rich literature review of the EDM work that has been published during the past 12 years (2007–2018) with focus on the prediction of academic performance in higher education. We analyze the most commonly used features and methods in predicting academic achievement, and highlight the benefits of the mostly used DM tools in EDM. The results of this paper could assist researchers and educational planners who are attempting to carry out EDM solutions in the domain of higher education as we highlight the type of features that the previous researches found to have significant impact on the prediction, as well as the benefits and drawbacks of the DM methods and tools used for predicting academic outcomes. [ABSTRACT FROM AUTHOR]

As universities around the world have begun to use learning management systems (LMSs), more learning data have become available to gain deeper insights into students' learning processes and make data‐driven decisions to improve student learning. With the availability of rich data extracted from the LMS, researchers have turned much of their attention to learning analytics (LA) applications using educational data mining techniques. Numerous LA models have been proposed to predict student achievement in university courses. To design predictive LA models, researchers often follow a data‐driven approach that prioritizes prediction accuracy while sacrificing theoretical links to learning theory and its pedagogical implications. In this study, we argue that instead of complex variables (e.g., event logs, clickstream data, timestamps of learning activities), data extracted from online formative assessments should be the starting point for building predictive LA models. Using the LMS data from multiple offerings of an asynchronous undergraduate course, we analysed the utility of online formative assessments in predicting students' final course performance. Our findings showed that the features extracted from online formative assessments (e.g., completion, timestamps and scores) served as strong and significant predictors of students' final course performance. Scores from online formative assessments were consistently the strongest predictor of student performance across the three sections of the course. The number of clicks in the LMS and the time difference between first access and due dates of formative assessments were also significant predictors. Overall, our findings emphasize the need for online formative assessments to build predictive LA models informed by theory and learning design. Practitioner notesWhat is already known about this topic Higher education institutions often use learning analytics for the early identification of low‐performing students or students at risk of dropping out.Most predictive models in learning analytics rely on immutable student characteristics (e.g., gender, race and socioeconomic status) and complex variables extracted from log data within a learning management system.Prioritizing prediction accuracy without theory orientation often yields "black‐box" models that fail to inform educators on what remedies need to be taken to improve student learning.What this paper adds Predictive models in learning analytics should consider learning theory, pedagogy and learning design to identify key predictors of student learning.Online formative assessments can be a starting point for building predictive models that are not only accurate but also provide educators with actionable insights on how student learning can be improved.Time‐related and score‐related features extracted from online formative assessments are particularly useful for predicting students' course performance.Implications for practice and/or policy This study provides strong evidence for using online formative assessments as the foundation for predictive models in learning analytics.Student data from online formative assessments can help educators provide students with feedback while informing future formative assessment cycles.Higher education institutions should avoid the hype around complex data from learning management systems and instead rely on effective learning tools such as online formative assessments to revolutionize the use of learning analytics. [ABSTRACT FROM AUTHOR]

For scholarly organizations, students' academic performance (AP) computes student achievements in different academic subjects. Therefore, a systematic literature review based on machine learning approaches to improve student performance is proposed. This field creates a way to discover hidden examples from instructive information. Machine learning (ML) techniques are used for performance prediction. It is become a challenge due to its imbalanced dataset. This review aims to identify the best proposals that focus on various ML methods used for the performance analysis of students. This review will become helpful to the teachers in identifying the weak students, and it helps to improve their performance through proper guidance. Thus, it reflects in the student's background and boosts their growth. It also brings benefits to students, teachers, and institutions. This study focused on applying machine learning techniques to predict students' performance in recent times. With a systematic approach, the research identified the existing prediction methods and tools used to predict students' performance and observed the researchers' type of variables in this research area. In this study, almost more than 100 papers were analyzed to reveal various modern techniques that are commonly used to predict student performance and the goals they need to achieve in this field. The results from the various research will help improve students' academics and monitor the student's performance, which would also improve their literacy rate. [ABSTRACT FROM AUTHOR]

Recently, educational institutions faced many challenges. One of these challenges is the huge amount of educational data that can be used to discover new insights that have a significant contribution to students, teachers, and administrators. Nowadays, researchers from numerous domains are very interested in increasing the quality of learning in educational institutions in order to improve student success and learning outcomes. Several studies have been made to predict student achievement at various levels. Most of the previous studies were focused on predicting student performance at graduation time or at the level of a specific course. The main objective of this paper is to highlight the recently published studies for predicting student academic performance in higher education. Moreover, this study aims to identify the most commonly used techniques for predicting the student's academic level. In addition, this study summarized the highest influential features used for predicting the student academic performance where identifying the most influential factors on student's performance level will help the student as well as the policymakers and will give detailed insights into the problem. Finally, the results showed that the RF and ensemble model were the most accurate models as they outperformed other models in many previous studies. In addition, researchers in previous studies did not agree on whether the admission requirements have a strong relationship with students' achievement or not, indicating the need to address this issue. Moreover, it has been noticed that there are few studies which predict the student academic performance using students' data in arts and humanities major. [ABSTRACT FROM AUTHOR]

This study introduces data mining methods to accounting education scholarship to explore the relationship between accounting students' current academic performance (grades), demographic information, pre-university entrance scores and predicted academic performance. It adopts a C4.5 classification algorithm based on decision-tree analysis to examine 640 accounting students enrolled in an undergraduate accounting program at an Australian university. A significant contribution of this study is improved prediction of academic performance and identification of characteristics of students deemed to be at risk. By partitioning students into sub-groups based on tertiary entrance scores and employing clustering of study units, this study facilitates a more nuanced understanding of predictor attributes. Key findings were the dominance of a cluster of second year units in predicting students' later academic performance; that gender did not influence performance; and that performance in first year at university, rather than secondary school grades, was the most important predictor of subsequent academic performance. [ABSTRACT FROM AUTHOR]

Student achievement prediction is one of the most important research directions in educational data mining. Student achievement directly reflects students' course mastery and lecturers' teaching level. Especially for the achievement prediction of college students, it not only plays an early warning and timely correction role for students and teachers, but also provides a method for university decision-makers to evaluate the quality of courses. Based on the existing research and experimental results, this paper proposes a student achievement prediction model based on evolutionary spiking neural network. On the basis of fully analyzing the relationship between course attributes and student attributes, a student achievement prediction model based on spiking neural network is established. The evolutionary membrane algorithm is introduced to learn hyperparameters of the model, so as to improve the accuracy of the model in predicting student achievement. Finally, the proposed model is used to predict student achievement on two benchmark student datasets, and the performance of the prediction model proposed in this paper is analyzed by comparing with other experimental algorithms. The experimental results show that the model based on spiking neural network can effectively improve the prediction accuracy of student achievement. [ABSTRACT FROM AUTHOR]

College context and academic performance are important determinants of academic success; using students' prior experience with machine learning techniques to predict academic success before the end of the first year reinforces college self-efficacy. Dropout prediction is related to student retention and has been studied extensively in recent work; however, there is little literature on predicting academic success using educational machine learning. For this reason, CRISP-DM methodology was applied to extract relevant knowledge and features from the data. The dataset examined consists of 6690 records and 21 variables with academic and socioeconomic information. Preprocessing techniques and classification algorithms were analyzed. The area under the curve was used to measure the effectiveness of the algorithm; XGBoost had an AUC = 87.75% and correctly classified eight out of ten cases, while the decision tree improved interpretation with ten rules in seven out of ten cases. Recognizing the gaps in the study and that on-time completion of college consolidates college self-efficacy, creating intervention and support strategies to retain students is a priority for decision makers. Assessing the fairness and discrimination of the algorithms was the main limitation of this work. In the future, we intend to apply the extracted knowledge and learn about its influence of on university management. [ABSTRACT FROM AUTHOR]

The tremendous growth in electronic educational data creates the need to have meaningful information extracted from it. Educational Data Mining (EDM) is an exciting research area that can reveal valuable knowledge from educational databases. This knowledge can be used for many purposes, including identifying dropouts or weak students who need special attention and discovering extraordinary students who can be offered lifetime opportunities. Although former studies in EDM used an extensive range of features for predicting students' academic achievement (in terms of (i) achieved grades or (ii) passing and failing), those features are sometimes not obtainable for practical usage, and therefore, the prediction models are not feasible for employment. This study uses data mining (DM) algorithms to predict the academic performance of master' s students by using a non-extensive data set and including only the features that are easy to collect at the beginning of a studying program. To perform this study, we have collected over 700 students' records from 2010 to 2018 from the Faculty of Business Informatics and Mathematics at the University of Mannheim in Germany. Those records include demographics and post-enrollment features such as semester grades. The empirical results show the following: (i) the most significant features for predicting students' academic achievements are the students' grades in each semester (importance rate between 14 and 36%), followed by the distance from students' accommodation to university (importance rate between 6 and 18%) and culture (importance rate between 7 and 17%). On the other hand, gender, age, the numbers of failed courses, and the number of registered and unregistered exams per semester are less significant for the predictions. (ii) As expected, predictions performed after the second semester is more accurate than those performed after the first semester. (iii) Unsurprisingly, models that predict two classes yield better results than those that predict three. (iv) Random Forest classifier performs the best in all prediction models (0.77–0.94 accuracy), and using oversampling methods to deal with imbalanced data can significantly improve the performance of DM methods. For future work, we recommend testing the predictive models on other master programs and a larger datasets. Furthermore, we recommend investigating other oversampling approaches. [ABSTRACT FROM AUTHOR]