Academic success is a goal for everyone in the academic community. However, this success can be hindered by various factors. Determining these factors is therefore crucial so that they can be dealt with beforehand and consequently come up with steps and solutions to deal with them. Artificial Intelligence has recently played a significant role in the academic field. Through what is now referred to as Educational Mining and Learning Analysis, big data from around the world are being put through machine learning algorithms to provide insights on achieving academic success. This study analyzes how a student’s environmental factors affect their scores. We use a dataset that includes 30000+ data with various independent variables, including gender, parent’s marital status, and study hours, i.e., to determine students’ scores in three courses: Reading, Writing, and Math. The research uses Logistic Regression, Artificial Neural Networks (ANN), Naïve Bayes, and Decision Tree algorithms as machine learning models named EGpM. The study showed that of the four models, Logistic Regression and Naïve Bayes were the most accurate, with 73.89% and 74.38%, respectively. ANN wasn’t far off with 73.63% accuracy, while Decision Tree was the least accurate with 64.12%.