•  
  •  
 

Keywords

associated factors, decision tree algorithms, educational data mining, numeracy skills

Abstract

Numeracy is a critical competency for academic and everyday functioning. This study investigates the key factors associated with students’ numeracy skills by employing decision tree algorithms as a data mining technique. The dataset used in this study is educational assessment data from Indonesia. Utilizing a dataset comprising 6,953 entries and 60 variables from Education Report, the research adopts an exploratory approach involving data preprocessing, exploratory data analysis, and decision tree model construction. The findings reveal that students’ literacy skills serve as the most dominant predictor of numeracy proficiency, emerging as the root node in the decision tree structure. Additional associated factors include psychological well-being, quality of learning environments, teacher competence, and school inclusivity. The decision tree model achieved a classification accuracy of 89.82% at optimal depth, enabling the derivation of interpretable decision rules for categorizing numeracy proficiency into four levels: far below minimum competency, below minimum competency, meeting minimum competency, and exceeding minimum competency. These results demonstrate the potential of decision tree algorithms to uncover complex interdependencies and inform data-driven educational policy and instructional interventions. The code and data used in this study are available upon request.

DOI

https://doi.org/10.5038/1936-4660.19.2.1494

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License

Download

Share

COinS