Comparative Analysis of Feature Selection Techniques in Predictive Modeling of Mathematics Performance: An Ecuadorian Case Study
Journal Title: Education Science and Management - Year 2023, Vol 1, Issue 2
Abstract
The field of educational research increasingly emphasizes predictive modeling of academic performance, focusing on identifying determinants of student success and crafting models to forecast future achievements. This investigation evaluates the efficacy of different feature selection techniques in predicting mathematics performance among Ecuadorian students, based on data from the 2021-2022 cycle of the Ser Estudiante test. Employing supervised logistic regression for classification, the study compares three feature selection methods: selection based on the highest k-scores, recursive feature elimination with cross-validation (RFECV), and recursive feature elimination (RFE). The assessment reveals that both the highest k-scores and RFECV methods are highly effective in isolating the most pertinent features for predicting mathematical prowess. These methods achieved prediction accuracies exceeding 90%, with k-scores attaining 96% and RFECV 92%. Furthermore, they demonstrated remarkable recall (94% and 97%, respectively) and F1-Score (96% and 91%, respectively). Additionally, both methods presented Receiver Operating Characteristic (ROC) curves with an area under the curve (AUC) of 99%, signifying superior discriminatory capability. The findings illuminate the critical role of judicious feature selection in enhancing the precision of predictive models for academic performance, particularly in mathematics. The results advocate for the application of these techniques in pinpointing key factors contributing to student success. This study not only contributes to the methodological discourse in educational data analysis but also provides practical insights for the Ecuadorian education system in leveraging data-driven approaches to enhance student outcomes.
Authors and Affiliations
Nadia N. Sánchez-Pozo, Liliana M. Chamorro-Hernández, Jorge Mina, Javier Montalvo Márquez
Keywords
Related Articles
- EP ID EP731804
- DOI 10.56578/esm010205
- Views 83
- Downloads 1
Evaluating Online Learning Adaptability in Students Using Machine Learning-Based Techniques: A Novel Analytical Approach
The widespread adoption of Learning Management Systems (LMSs) in educational contexts, underscored by their critical role in facilitating cloud-based training across diverse settings, serves as the foundation of this inv...
The Application of Fuzzy Multi-Criteria Methods for the Selection of Digital Platforms for the Improvement of the Learning Process at Universities in the Brčko District of BiH
The selection of appropriate digital platforms (DPs) for enhancing the learning process at universities in the Brčko District, Bosnia and Herzegovina (BiH), was explored through the application of fuzzy multi-criteria de...
Exploring the Influence of Returnees’ Scientific Collaboration Networks on Research Performance
Returnee faculty play a pivotal role in international knowledge transfer and the advancement of scientific research within domestic universities. However, the effectiveness of returnees in enhancing institutional researc...
Examining the Mediating Role of Job Satisfaction between Motivation, Organizational Culture, and Employee Performance in Higher Education: A Case Study in the Arab Region
This study aimed to examine the correlation among motivation, organizational culture and employee performance and the mediation role of job satisfaction in higher education. A more productive and positive work environmen...
Design and Development of an Art Appreciation Learning Kit for Children Aged 7-11: Enhancing Aesthetic Engagement Through the “See, Think, Wonder” Thinking Routine
In the context of rapidly advancing digital technology, where touchscreen interactions dominate, the tactile sensory development of children is increasingly compromised. This shift towards digital media can hinder the ab...