What does this research mean for the field?

Machine learning models can accurately predict students' learning styles based on demographic and behavioral characteristics. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The research aims to predict students' learning styles using various machine learning models based on their demographics and behaviors.

February 26, 2026Open Access

Predicting Students’ Learning Stylesusing Machine Learning

Key Points

The research aims to predict students' learning styles using various machine learning models based on their demographics and behaviors.
Collected data from engineering and non-engineering students including demographics and study preferences.
Analyzed key attributes like CGPA, study hours, and preferred study times.
Applied multiple supervised machine learning models to predict learning styles.
Identified effective machine learning classifiers for predicting learning styles.
Demonstrated the applicability of ML algorithms in understanding student behaviors.
Enhanced potential for developing adaptive learning technologies.

Abstract

Understanding Learning Styles (LS) of students in the times of Artificial Intelligence (AI) can be beneficial for students’ success. Current ‎study investigates the applicability of several supervised Machine Learning (ML) models to envisage students' learning styles based on ‎demographic and behavioral characteristics. The data, collected from both engineering and non-engineering students viz. commerce, science, ‎and arts, includes male and female students in the age range of 17 to 30 years. CGPA (on 10-point scale), study hours (weekly), and pre-‎ferred study times (viz. morning, afternoon, evening, and late night), were considered as the key attributes of research. This research at-‎tempts to discover the abilities of ML classifiers for precise prediction of student's learning style from diverse and multi-dimensional data. ‎Further analysis is done to identify the best performing algorithms aiming towards the development of adaptive learning technologies in ‎educational settings‎.

Bookmark

View Full Paper