A Cloud Based Web-Tool to Predict the High School Entrance Exam Scores of the Students

Authors : Gokcen Altun, Ekrem Gülcüoğlu

Pages : 667-684

Doi:10.29130/dubited.1535345

View : 37 | Download : 25

Publication Date : 2025-04-30

Article Type : Research Paper

Abstract :Multivariate adaptive regression splines (MARS) model, one of the non-parametric regression methods, is used to predict the achievement scores of the 8th-grade students before the LGS (High School Entrance System) exam with the developed web-tool. The demographic information of the students and all the test results they took in the last year are used before the LGS exam. The significant variables on the LGS scores of the students are the number of siblings, mother\\\'s education level, revolution history and Kemalism, English, mathematics courses. A web-based machine learning-based application has been developed to predict the LGS scores of the students in line with these data. The web-tool is accessible with the following website https://beststat.shinyapps.io/lgs2/. R Shiny program is used in the development of the web-tool. The program is cloud-based and works independently of the operating system and web browsers. The developed application helps students prepare for the LGS exam to offer pre-exam advice to guide their studies.
Keywords : : MARS, Makine öğrenimi, LGS, Öğrenci başarısı, Veri madenciliği, R Shiny.