Predicting Critical Courses in Retention of Bachelor of Science in Architecture

Abstract

The study of architecture can be said to be challenging, interesting, and not an easy profession because having artistic skills is one of the most important parts of this course as it requires a lot of drawing skills and creativity. To predict and identify courses that are necessary for BS Architecture retention, this study proposed a unique architecture that makes use of educational data mining techniques. This paper presented an experimental investigation based on actual data from the BS Architecture course at Cavite State University. In this study, machine learning models were used to estimate the ranking of subjects that are important for students to pass based on the information on previous academic performance. Furthermore, mathematics performance had a significant impact on the academic progress of architecture students. By analyzing this proposition, this paper contributes to the current topic of the relationship between important subjects in the retention of BS Architecture and undergraduate academic success. The possibility of using grades in mathematics and major disciplines as a predictor of academic achievement in undergraduate architecture programs is one of the problems identified by these findings. In addition, this work uses WEKA as data mining software, and the modeling technique used is Random Forest. Overall, the model can be a very useful tool for
completing the program.