Predicting Students’ Learning Stylesusing Machine Learning

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.