Analysis of graduation prediction on time based on student academic performance using the Naïve Bayes Algorithm with data mining implementation (Case study: Department of Industrial Engineering USU)
Mariani Sembiring, Ratu H Tambunan · IOP Conference Series Materials Science and Engineering · 2021
Abstract One indicator of higher education performance is student graduation presentation on time with a passing percentage of more than or equal to 50%. The abundance of data in the Higher Education Academic Information System (SIA) is not used in measuring the performance of a College, especially the Study Program. The Industrial Engineering Department summarizes student data in the SIA as a database and processes it according to what is needed. During this time, the data were abundant in SIA has not been utilized to assess student performance. When the Study Program conducts a student academic evaluation, the Study Program evaluates it based on the variable number of credits, GPA, and constraints. In the Study Program, an appropriate classification is needed to make it easier to evaluate student performance. The method that is used is the Naïve Bayes algorithm in classifying students’ academic performance USU Department of Industrial Engineering. Attributes are used, among other NIM, Name, Gender, Region of Origin, Origin School, Entrance, and GPA. From the results of testing 173 sample data using the Naïve Bayes algorithm, the pattern formed has a match accuracy of 70.83%, which means that it is useful in predicting student graduation.