Determining the Level of Adaptability of Students in Online Education Using Machine Learning Algorithms

Asencios-Trujillo L.V.; Asencios-Trujillo L.; La-Rosa-Longobardi C.J.; Gallegos-Espinoza D.; Piñas-Livia C. · International Journal of Engineering Trends and Technology (2025) · DOI: 10.14445/22315381/ijett-v73i1p125

Resumen

In the context of online education, student adaptability is a critical factor for their success. This study aims to predict the level of adaptability of students in online education environments using Machine Learning models. A dataset of 1205 records was used, which includes several demographic and contextual characteristics, such as age, gender, educational level, and type of institution, among others. Data preprocessing included the transformation of categorical features using one-hot encoding. The dataset was then divided into training and test sets to evaluate the model’s performance. The Random Forest algorithm was selected for the classification task due to its ability to handle data with multiple characteristics and its robustness against overfitting. The results show that the Random Forest model achieved an accuracy of 91.29% in predicting the level of adaptability. The recall and f1-score values for the different categories (“Low”, “Moderate”, “High”) indicated good performance, especially for the “Low” and “Moderate” categories. All information collected for this study is anonymous, ensuring data privacy. The dataset includes data at the national and international levels, providing a broad and generalizable perspective.

Instituciones: Universidad Nacional de Educación Enrique Guzmán y Valle