A Machine Learning-based Automatic Model to Predicting Performance of Students

Machine learning offers a variety of techniques for use in diverse fields. Massive quantities of student data are produced in educational institutions, and machine-learning techniques are a precious tool for identifying patterns in individuals' behavior. Academicians can learn valuable data concerning the students' expertise and how it relates to their educational assignments by critically examining and evaluating these data. This data serves as the input for cutting-edge techniques and algorithms that can forecast students' academic achievement. This research presents a machine learning-based automatic model for predicting the performance of students. The popular ML methods are Random Forest, K-Neighbors, Extra Trees, Ada-Boost, Decision Tree, Logistic Regression, Gaussian NB, and Bernoulli NB. This research utilizes an online student performance dataset collected from Kaggle. The findings demonstrate that Random forest and decision trees outperform other techniques based on high precision as well as the capacity to interpret the guidelines and structure that were developed for predicting students' educational success.