Classification of Children's Numerical Intelligence Levels Based on Mathematics Learning Activities Using Machine Learning

Aug 3, 2026

Numerical ability plays a decisive role in educational success and logical thinking development, yet mathematics instruction in Islamic boarding schools often faces constraints such as limited technology integration and narrow learning resources. This study evaluates children’s numerical intelligence levels through machine learning, using Decision Tree and Random Forest classifiers. Questionnaire data capture study duration, practice frequency, learning methods, classroom engagement, and problem-solving speed. After preprocessing, models are assessed via confusion matrices and cross-validation, yielding 86% accuracy for Decision Tree and 92% for Random Forest. Results indicate that practice frequency and engagement are key predictors and support more personalized teaching.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Background and key challenges in pesantren mathematics learning

Role of machine learning and selected algorithms

Related work and research motivation

Classification of Children's Numerical Intelligence Levels Based on Mathematics Learning Activities Using Machine Learning Sandy Suryantiko1)*, Gilang Adriana Mulyadi2), Ferawati3) 1)2)3) Department of Informatics Engineering, Faculty of Information and Communication Technology Faculty, Institut Teknologi dan Bisnis Bina Sarana Global, Tangerang, Indonesia 1)[dentsandy3461@gmail.com](dentsandy3461@gmail.com) 2)[gilangadrianamulyadi@gmail.com](gilangadrianamulyadi@gmail.com) 3)[ferawati@global.ac.id](ferawati@global.ac.id) Article history: Received 13 June 2025; Revised 17 June 2025; Accepted 23 June 2025; Available online 10 August 2025 Keywords: Decision Tree Machine Learning Mathematics Learning Numerical Intelligence Random Forest Abstract Numerical ability is a critical aspect of education that impacts both academic achievement and the development of logical thinking skills. However, in Islamic boarding schools (pondok pesantren), the teaching of mathematics often encounters limitations such as a lack of technological integration and diverse learning resources. This study aims to assess students' numerical intelligence levels based on their mathematics learning activities using machine learning techniques, specifically Decision Tree and Random Forest algorithms. Data was collected through questionnaires that captured key variables such as study duration, frequency of practice, learning methods, class engagement, and the speed of problem-solving. After data preprocessing, both models were evaluated through confusion matrices and cross-validation to determine their classification accuracy and stability. The findings revealed that the Decision Tree model achieved an accuracy rate of 86%, while the Random Forest model surpassed it with a 92% accuracy rate, showing more consistent performance. This study highlights the potential of machine learning to enhance educational outcomes, particularly in pesantren settings, by offering deeper insights into students'learning patterns. Beyond classification accuracy, machine learning helps educators identify key factors influencing students' numerical intelligence. The Random Forest model, in particular, revealed that variables such as practice frequency and student engagement are significant predictors of numerical intelligence levels. This information can be used to develop more personalized and effective teaching strategies aimed at improving students' mathematical skills. I. INTRODUCTION Mathematics is one of the core subjects in the education system, playing an essential role in developing logical and analytical thinking skills. However, many students, especially in Islamic boarding schools (pondok pesantren), struggle to deeply understand mathematical concepts. This difficulty can be attributed to various factors, such as a lack of interactive teaching methods, limited learning resources, and low motivation to practice problems independently. According to Aulia et al. [1] ., children with lower emotional intelligence tend to grasp the concept of sets more quickly, while those with lower emotional intelligence face more challenges in understanding various other aspects. Therefore, more effective strategies are needed to identify student learning patterns in order to enhance their numerical intelligence. Teachers can improve children’s intelligence through direct, indirect, and group methods. Indirect and group strategies are considered more effective. Group interaction increases student engagement, and the use of visual media such as images and numbers can enhance logical thinking and problem-solving skills. Hence, new exploratory methods must be developed consistently to strengthen logical intelligence from an early age [2] .. * Sandy Suryantiko One of the main challenges in the learning system at Islamic boarding schools is the minimal use of technology to support the teaching and learning process. With the advancement of technology, the concept

FAQs

What is the main objective of the study?

To classify children’s numerical intelligence levels based on their mathematics learning activities using machine learning models.

Which machine learning algorithms are used and why?

Decision Tree and Random Forest are used because they are effective for classification, and Decision Tree provides interpretable decision paths for understanding key factors.

How is model performance evaluated?

Through data preprocessing followed by evaluation using confusion matrices and cross-validation to measure accuracy and stability.

Aug 3, 2026

Upload by Seraphina