Influence Analytics Model of the General Education Courses Toward the Academic Achievement of Rajabhat University Students Using Data Mining Techniques

The fundamental structure and critical component of learner development are to provide basic knowledge for sustainable development and lifelong learning. Therefore, providing knowledge in essential matters is included in every educational curriculum in Thailand. This research has three main objectives: to study the context of academic achievement from the influence of general education courses on students in Rajabhat University, to study student cluster behaviors influenced by general education courses, and to manufacture a predicting model for risk groups of learners affected by general education courses. The demographic data and the sample are 367 students from the Faculty of Science and Technology, Rajabhat Maha Sarakham University, during the academic year 2011–2018, from the Bachelor of Science Program in Computer Science. The research tools were descriptive, diagnostic, and predictive analytics, including Mean, Mode, Median, Minimum, Maximum, K-Means, Decision Trees, Naïve Bayes, K-NN, Cross-Validation, Confusion Matrix, Accuracy, Precision, Recall, and F1-Score. The results showed that the risk groups that students will not graduate were significant of two clusters obtained from the research with learning achievement behaviors influenced by general education courses. In addition, the resulting model has the potential and ability to predict the possibility that the learners will not achieve academic achievement at a very high level, with a model accuracy of 87.19%. With the research results that have been studied, researchers can use the results to devise strategies to prevent future dropouts from the higher education system.