Paper Title
Enhancing Academic Success: A Hybrid Explainable AI and Random Forest Approach for Predicting Student Performance

Abstract
Considering the goal of improving learning outcomes, this study investigates the field of education by predicting students’ performance on final exams. For a deeper understanding, we suggest a hybrid model that combines Explainable Artificial Intelligence (XAI) with Random Forest’s accuracy. The approach makes use of a large dataset that includes information on 395 students’ past academic performance, learning styles, family history, and health. Once careful model selection and data pretreatment are done, Random Forest is the best way to capture complex relationships in the data. The research not only improves learning outcomes but also adds to the current debate in education by bringing forward practical solutions that result from predictive insights, creating a more knowledgeable and fair educational environment. By utilizing explainable AI, this research goes beyond basic prediction and offers useful insights into the factors that influence students’ success. Educators and other stakeholders can use this information to create targeted strategies and support systems that will ultimately improve learning outcomes and create a more equal learning environment for all children. Keywords - Student Performance Prediction, Explainable AI (XAI), Random Forest, Learning Outcomes Improvement, Educational Equity