Automatic detection of students at risk of dropping out of school using mRMR and Late Fusion

Medina, Daniel Zapata; Builes, Jovani Alberto Jiménez; Bedoya, Albeiro Espinosa

doi:10.1109/jicv56113.2022.9934262

Cited by 1 publication

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, educational databases include relevant information on student demographics to identify their social environment. The availability of this information can improve communication between the educational institution, the family, and the community, which in turn can positively impact the quality of school life [33]. On the other hand, academic features are related to different aspects of the student's learning process, including cognitive, procedural, and attitudinal aspects.…”

Section: Related Workmentioning

confidence: 99%

“…In this study, the mRMR method is applied to select the subset of features most influential in school dropout. To achieve this discrimination, the quotient of relevance (c|x i ) over redundancy (x|x i−1 ) is calculated for each class-feature pair to select the feature whose score is higher [33].…”

Section: Discriminant Analysismentioning

confidence: 99%

“…a Sisbén: System for the Identification of Potential Beneficiaries of Social Programs. Source: Authors, adapted from[33].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Improving the Automatic Detection of Dropout Risk in Middle and High School Students: A Comparative Study of Feature Selection Techniques

Zapata-Medina,

Espinosa-Bedoya,

Jiménez-Builes

2024

Mathematics

View full text Add to dashboard Cite

The dropout rate in underdeveloped and emerging countries is a pressing social issue, as highlighted by studies conducted by The Organization for Economic Co-operation and Development. This study compares five feature selection techniques to address this challenge and improve the automatic detection of dropout risk. The methodological design involves three distinct phases: data preparation, feature selection, and model evaluation utilizing machine learning algorithms. The results demonstrate that (1) the top features identified by feature selection techniques, i.e., those constructed through feature engineering, proved to be among the most effective in classifying student dropout; (2) the F-score of the best model increased by 5% with feature selection techniques; and (3) depending on the type of feature selection, the performance of the machine learning algorithm can vary, potentially increasing or decreasing based on the sensitivity of features with higher noise. At the same time, metaheuristic algorithms demonstrated significant precision improvements, but there was a risk of increasing errors and reducing recall.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Discriminant Analysismentioning

confidence: 99%