Predicting student performance academic using Automated Machine Learning (AutoML): in medical academic institutions

Abstract Educational institutions seek to increase distinguished educational programs, and these programs increase costs and expenses of these institutions consuming a lot of their budget. More attention is being paid by educational institutions to keeping students in their programs without lowering educational standards or making it difficult for them to learn. Big data enables universities to predict future student outcomes more accurately. The population of the study includes students enrolled in an academic course at Damietta University between 2016 and 2021, the sample size used for the study consists of 461 student records after preprocessing, and the study was conducted at academic institution affiliated with Damietta University, Egypt. The main aim herein is to determine the best and most accurate algorithms which would enable forecasting students' academic performance, and therefore allowing medical sector college's decision makers in amending admission systems and methods in selecting students through the use of statistics and grades that have been available in the last five years.