Early Prediction of Students at Risk of Failing a Face-to-Face Course in Power Electronic Systems

Alcaraz, Raúl; Martínez-Rodrigo, Arturo; Zangróniz, Roberto; Rieta, J.J.

doi:10.1109/tlt.2021.3118279

Cited by 10 publications

(14 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GBM was the best approach for subjective predictors, BA-RS for the objective predictors, and RF for the combined sets. The highest predictive performance of RF is congruent with the existing literature in Learning Analytics, where RF consistently ranks among the best models [55], [56]. To the best of our knowledge, our second best approach, Bayesian multilevel models with random slopes, is not mentioned in any LA studies, due to its nature as a statistical approach.…”

Section: Discussionsupporting

confidence: 81%

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Imhof

Comşa

Hlosta

et al. 2023

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

Procrastination, the irrational delay of tasks, is a common occurrence in online learning. Potential negative consequences include higher risk of drop-outs, increased stress, and reduced mood. Due to the rise of learning management systems and learning analytics, indicators of such behavior can be detected, enabling predictions of future procrastination and other dilatory behavior. However, research focusing on such predictions is scarce. Moreover, studies involving different types of predictors and comparisons between the predictive performance of various methods are virtually non-existent. In this study, we aim to fill these research gaps by analyzing the performance of multiple machine learning algorithms when predicting the delayed or timely submission of online assignments in a higher education setting with two categories of predictors: subjective, questionnaire-based variables and objective, log-data based indicators extracted from a learning management system. The results show that models with objective predictors consistently outperform models with subjective predictors, and a combination of both variable types perform slightly better with an accuracy of 70%. For each of these three options, a different approach prevailed (Gradient Boosting Machines for the subjective, Bayesian multilevel models for the objective, and Random Forest for the combined predictors). We conclude that careful attention should be paid to the selection of predictors and algorithms before implementing such models in learning management systems.

show abstract

Section: Discussionsupporting

confidence: 81%

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Imhof

Comşa

Hlosta

et al. 2023

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

show abstract

“…No Approach Paper 1 Academic Performance Prediction [11], [12], [17], [18], [23], [24], [35], [37], [38], [41], [44], [45], [51], [56], [57], [64], [71], [74], [75], [78], [80], [81], [84] 2 At-Risk Student Prediction [1], [9], [10], [13], [19], [36], [50], [55], [59], [62], [65], [66], [73], [77], [79], [82] 3 Dropout/Graduation Prediction [14], [15], [20], [21], [47], [48], [54], [60], [61], [63], [72],…”

Section: Table 4 Mapping Of Approachesmentioning

confidence: 99%

“…Machine learning techniques are used to forecast student academic achievement in a smart campus setting, specifically to discover the characteristics that contribute to student success and execute suitable strategies to improve their achievement [12]. The early identification of students with the possibility of failing in face-to-face courses is also applicable [13]. To boost the prediction performance of students who are likely to drop out, a two-layer ensemble machine learning method is employed [14].…”

Section: Introductionmentioning

confidence: 99%

Predicting University Student Graduation Using Academic Performance and Machine Learning: A Systematic Literature Review

Pelima,

Sukmana,

Rosmansyah

2024

IEEE Access

View full text Add to dashboard Cite

Predicting university student graduation is a beneficial tool for both students and institutions. With the help of this predictive capacity, students may make well-informed decisions about their academic and career paths, and institutions can proactively identify students who may not graduate and offer tailored support to ensure their success. The use of machine learning for predicting university student graduation has drawn more attention in recent years. Large datasets of student academic performance data can be used to train machine learning algorithms to identify patterns that are applicable in predicting future outcomes. In accordance with some studies, this approach predicts student graduation with an accuracy rate as high as 90%. Many SLRs have been conducted in this field, but there are still limitations, including not discussing the predictive models and algorithms used, a lack of coverage of the machine learning algorithms applied, small database coverage, keyword selection that does not cover all synonyms relevant to the investigation, and less specific data collection transparency. By delving into the limitations of existing SLRs on this topic, this research not only enhances the understanding of machine learning applications in forecasting student graduation but also fills a crucial gap in the literature. The inclusion of weaknesses in current SLRs provides a foundation for justifying the need for this study, emphasizing the necessity of a more nuanced and comprehensive review to advance the field and guide future research efforts in smart learning environments. This research conducts a thorough systematic review of the existing literature on machine learning-based student graduation prediction models from 70 journal articles from 2018 through 2023 that are pertinent. This review includes the various machine learning algorithms that have been implemented, the various academic performance data that was obtained from students, and the effectiveness of the models that have been developed. It also discusses the difficulties and potential advantages of utilizing machine learning to predict student graduation. The review indicates that the most common approach employed is the prediction of students' academic performance, which relies on data obtained from the Learning Management System and Student Information System. The primary data utilized for prediction purposes consists Student retention and time of academic and behavioral information. Among the various algorithms employed, Support Vector Machine and Random Forest are the most commonly utilized. This study makes a significant contribution to the advancement of learner modules within the smart learning environment.

show abstract

“…For example, in developing an early prediction of students at risk of failing a face-to-face course in power electronic systems, the scrutinized classifiers have demonstrated notable effectiveness in the identification of students at risk of course failure. Indeed, significant accuracy and sensitivity values ranging from 70% to 81% were observed, even when exclusively considering attributes from the students' background [62]. Thus, in this section, we will review some classification algorithms in displaying their application in classification tasks:…”

Section: Classification Algorithmsmentioning

confidence: 99%

Feature selection techniques and classification algorithms for student performance classification: a review

Alias,

Hambali,

Abdul Aziz

et al. 2024

IJECE

View full text Add to dashboard Cite

The process of categorizing students’ performance based on input data, encompassing demographic information and final exam results, is recognized as student performance classification. Educational data mining has gained traction in assessing students’ performance. However, this study entails the need to analyze the diverse attributes of students’ information within an educational institution by using data mining techniques. This study thoroughly examines both previous and current methodologies presented by researchers, addressing two main aspects: data preprocessing and classification algorithms applied in student performance classification. Data preprocessing specifically delves into the exploration of feature selection techniques, encompassing three types of feature selection and search methods. These techniques aim to identify the most significant features, eliminate unnecessary ones, and reduce data dimensionality. In addition, classification algorithms play a crucial role in categorizing or predicting student performance. Models such as k-nearest neighbors (KNN), decision tree (DT), artificial neural networks (ANN), and linear models (LR) were scrutinized based on their performance in prior research. Ultimately, this study highlights the potential for further exploration of feature selection techniques like information gain, Chi-square, and sequential selection, particularly when applied to new datasets such as students’ online learning activities, utilizing a variety of classification algorithms.

show abstract

Early Prediction of Students at Risk of Failing a Face-to-Face Course in Power Electronic Systems

Cited by 10 publications

References 45 publications

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Predicting University Student Graduation Using Academic Performance and Machine Learning: A Systematic Literature Review

Feature selection techniques and classification algorithms for student performance classification: a review

Contact Info

Product

Resources

About