Educational Program Recommendation System for High School Students in Thailand Rural Cities
The learning styles of students living in rural cities and urban cities are completely different. Offering educational programs that are appropriate for the student's potential will help students succeed in learning. Therefore, this research aims to develop an educational prediction model and online application development guidelines to recommend appropriate educational programs for students at the secondary school in Thai rural cities. The data collection of 188 students were from four groups at Huaima Wittayakom School, Phrae Province, Thailand. It consisted of 63 students from the academic year 2009-2014, 42 students from the academic year 2010-2015, 50 students from the academic year 2011-2016, and 33 students from the academic year 2012-2017. The tools used for analysis are machine learning as known as decision tree. From the results, it was found that the factors (courses) related to the decision tree prediction model, which had been divided into six factors, were IT-31201, SC-23202, SO-21101, SC-21202, SC-22202, and EN-21102. At the same time, all of the models' performance testing results were at the highest level as summarized in this research. The results of this research were reasonable for being distributed and to be applied in other schools.