Predicative analysis of student performance in online learning
Keywords:
student engagement, binary classification, Random Forest, machine learning, educational technology, digital education, adaptive learningAbstract
Student engagement plays a vital role in ensuring effective learning outcomes, especially in digital education settings. This study presents a machine learning approach to classify engagement levels as "engaged" or "not engaged" using the Student Engagement Level-Binary dataset. The Random Forest algorithm was utilized, achieving an exceptional accuracy of 100%, showcasing its ability to identify patterns and deliver highly reliable predictions. The trained model has been stored as “student engagement model.pkl”, enabling seamless deployment in real-time educational applications, such as engagement monitoring and adaptive learning platforms. These findings demonstrate the value of leveraging data-driven techniques to support personalized and timely interventions for improved learning experiences. Future research will focus on validating the model with larger datasets and exploring its integration into scalable, real-world systems.
Downloads
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.