Early Prediction of student’s Performance in Higher Education: A Case Study

Martins, M. V.; Tolledo, Daniel; Machado, Jorge; Baptista, Luís; Realinho, Valentim

doi:10.1007/978-3-030-72657-7_16

Cited by 20 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Online News Popularity dataset, sourced from the website (www.mashable.com, accessed on 22 June 2023) and made available by [28], focuses on regression and aims to predict news popularity. Student Archive, provided by [29], was developed as part of a project to identify at-risk students early in their academic journey using machine learning technology; the dataset encompasses three types of classification tasks (dropout, enrollment, and graduates). The Superconductivity dataset, obtained from [30], pertains to superconducting materials and is used for regression to predict the critical temperature.…”

Section: Methodsmentioning

confidence: 99%

A Data Feature Extraction Method Based on the NOTEARS Causal Inference Algorithm

Wang

Zhu

2023

Applied Sciences

View full text Add to dashboard Cite

Extracting effective features from high-dimensional datasets is crucial for determining the accuracy of regression and classification models. Model predictions based on causality are known for their robustness. Thus, this paper introduces causality into feature selection and utilizes Feature Selection based on NOTEARS causal discovery (FSNT) for effective feature extraction. This method transforms the structural learning algorithm into a numerical optimization problem, enabling the rapid identification of the globally optimal causality diagram between features and the target variable. To assess the effectiveness of the FSNT algorithm, this paper evaluates its performance by employing 10 regression algorithms and 8 classification algorithms for regression and classification predictions on six real datasets from diverse fields. These results are then compared with three mainstream feature selection algorithms. The results indicate a significant average decline of 54.02% in regression prediction achieved by the FSNT algorithm. Furthermore, the algorithm exhibits exceptional performance in classification prediction, leading to an enhancement in the precision value. These findings highlight the effectiveness of FSNT in eliminating redundant features and significantly improving the accuracy of model predictions.

show abstract

Section: Methodsmentioning

confidence: 99%

A Data Feature Extraction Method Based on the NOTEARS Causal Inference Algorithm

Wang

Zhu

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The key factors they identified include misconceptions relating to cognitive load, social and family, motivational, technological constraints and the digital natives, lack of instructor understanding of online students, faculty limitations of using technology, and institution limitations to training faculty. Martins et al (2021) compare several machine learning models for predicting students' academic success. They tested logistic regression, support vector machine, decision tree, and random forest classifier and found that the random forest classifier outperformed the other model when prediction accuracy and average F1-score were used as the metrics.…”

Section: Literature Reviewmentioning

confidence: 99%

“…It can be downloaded via the research entry "Predict students' dropout and academic success" at www.researchgate.net. A subset of the data was used in the publication "Early Prediction of Student's Performance in Higher Education: A Case Study" (Martins, et al, 2021).…”

Section: Data Descriptionmentioning

confidence: 99%

“…Target represents the outcome of the college students: Graduate, Enrolled, and Dropout. The case study by Martins et al (2021) processed the data further to classify the students based on the length of time to Success, Relative Success, and Failure. Since our study focuses on student persistence.…”

Section: Data Descriptionmentioning

confidence: 99%

“…Previous studies have noted that the Random Forest model often performs better than the logistic regression model in many cases (e.g., Martins et al, 2021, Yağcı, 2022. We use the Random Forest Classifier from the scikit-learn machine learning library.…”

Section: Random Forest Classifiermentioning

confidence: 99%

See 2 more Smart Citations

Exploring Individual Feature Importance in Student Persistence Prediction

2023

JHETP

View full text Add to dashboard Cite

Student persistence is of great importance for all stakeholders in higher education. There have been numerous studies using data mining and machine learning tools to predict student persistence. However, very little research has explored individual feature importance and their distinctive roles in predicting individual outcomes. In this study, we compare the predictive performance of two widely used machine learning models, logistic regression, and random forest, and use the SMOTE to improve the model performance. We analyze the feature importance in both aggregated form and their varied impact on individual predictions using a real-world student persistence dataset. In the discussion section, we propose practical approaches for monitoring and predicting student persistence.

show abstract

A study of online academic risk prediction based on neural network multivariate time series features

Wu,

Yu,

Huang

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryNeural networks are becoming increasingly widely used in various fields, especially for academic risk forecasts. Academic risk prediction is a hot topic in the field of big data in education that aims to identify and help students who experience great academic difficulties. In recent years, the use of machine learning algorithms and deep learning algorithms to achieve academic risk prediction has garnered increased attention and development. However, most of these studies use nontime series data as features for prediction, which are slightly insufficient in terms of timeliness. Therefore, this article focuses on time series data features that are more expressive of changes in students' learning status and uses multivariate time series data as predictive features. This article proposes a method based on multivariate time series features and a neural network to predict academic risk. The method includes three steps: first, the multivariate time series feature is extracted from the interaction records of the students' online learning platforms; second, the multivariate time series feature transformation model ROCKET is applied to convert the multivariate time series feature into a new feature; third, the new feature is converted into a final prediction result using a linear classification model. Comparative tests show that the proposed method has high effectiveness.

show abstract

Early Prediction of student’s Performance in Higher Education: A Case Study

Cited by 20 publications

References 18 publications

A Data Feature Extraction Method Based on the NOTEARS Causal Inference Algorithm

A Data Feature Extraction Method Based on the NOTEARS Causal Inference Algorithm

Exploring Individual Feature Importance in Student Persistence Prediction

A study of online academic risk prediction based on neural network multivariate time series features

Contact Info

Product

Resources

About