University of Kashan Soft Computing Journal 2322-3707 9 2 2021 02 19 Predicting the academic status of admitted applicants based on educational and admission data using data mining techniques Predicting the academic status of admitted applicants based on educational and admission data using data mining techniques 94 113 111577 10.22052/scj.2021.242837.0 FA Arash Khosravi Department of Computer Engineering, Faculty of Engineering, Mahallat Institute of Higher Education, Mahallat, Iran. Hadi Abdulmaleki Department of Computer Engineering, Faculty of Electrical, Computer and Medical Engineering, Shahab Danesh Institute of Higher Education, Qom, Iran. Mehri Fayazi Department of Computer Engineering, Faculty of Engineering, Qom University, Qom, Iran. Journal Article 2021 02 08 Educational data mining has become an increasingly popular field of research in recent years due to the vast amount of student data held by educational institutions. This data can be utilized as a tool to improve the quality of education by extracting knowledge that can assist institutions in enhancing their teaching methods, learning processes, and decision-making. The purpose of this paper is to predict the educational status of students who are intending to continue their studies from an associate degree to a bachelor's degree. As the Ministry of Science plans to eliminate the entrance exam, universities are faced with the challenge of selecting students based on what criteria. To address this issue, data mining techniques such as decision tree, Naïve Bayes, neural network, support vector machine, random forest, Bagging, and Boosting were employed to analyze the educational information of new students. Then, by comparing this information with that of graduate, dropout, and expelled students at the bachelor's level, a more effective method for selecting students was proposed. The results indicate that random forest has the highest accuracy at 92.28%, while Naïve Bayes has the lowest accuracy at 61.09% in predicting educational status.  Educational data mining has become an increasingly popular field of research in recent years due to the vast amount of student data held by educational institutions. This data can be utilized as a tool to improve the quality of education by extracting knowledge that can assist institutions in enhancing their teaching methods, learning processes, and decision-making. The purpose of this paper is to predict the educational status of students who are intending to continue their studies from an associate degree to a bachelor's degree. As the Ministry of Science plans to eliminate the entrance exam, universities are faced with the challenge of selecting students based on what criteria. To address this issue, data mining techniques such as decision tree, Naïve Bayes, neural network, support vector machine, random forest, Bagging, and Boosting were employed to analyze the educational information of new students. Then, by comparing this information with that of graduate, dropout, and expelled students at the bachelor's level, a more effective method for selecting students was proposed. The results indicate that random forest has the highest accuracy at 92.28%, while Naïve Bayes has the lowest accuracy at 61.09% in predicting educational status.  https://scj.kashanu.ac.ir/article_111577_19f15e526a828df055970a61c557bb65.pdf