Temporal Prediction on Students’ Graduation using Naïve Bayes and K-Nearest Neighbor Algorithm

Ahmad Marzuqi,Ibnu Asror,Kusuma Ayu Laksitowening

doi:10.30865/mib.v5i2.2919

Abstract

Accreditation is a form of assessment of the feasibility and quality of higher education. One of the accreditation assessment factors is the percentage of graduation on time. A low percentage of on-time graduations can affect the assessment of accreditation of study programs. Predicting student graduation can be a solution to this problem. The prediction results can show that students are at risk of not graduating on time. Temporal prediction allows students and study programs to do the necessary treatment early. Prediction of graduation can use the learning analytics method, using a combination of the naïve bayes and the k-nearest neighbor algorithm. The Naïve Bayes algorithm looks for the courses that most influence graduation. The k-nearest neighbor algorithm as a classification method with the attribute limit used is 40% of the total attributes so that the algorithm becomes more effective and efficient. The dataset used is four batches of Telkom University Informatics Engineering student data involving data index of course scores 1, level 2, level 3, and level 4 data. The results obtained from this study are 5 attributes that most influence student graduation. As well as the results of the presentation of the combination naïve bayes and k-nearest neighbor algorithm with the largest percentage yield at level 1 75.40%, level 2 82.08%, level 3 81.91%, and level 4 90.42%.

Highlights

Accreditation is a form of evaluation or assessment of the quality and feasibility of a higher education institution or study program conducted by an organization or the National Accreditation Board for Higher Education (BANPT) [1]
The selection of this attribute uses a bernoulli naive bayes algorithm, so the data is first converted into binary form (0 & 1) by using the median dataset used. These results were obtained by using the 2008 student dataset level 1 to 4; this dataset was chosen because it has more student data than other datasets. These test results are in the form of subject attributes that have the most influence on student graduation
The conclusion from the implementation and analysis of the overall combination model of the naïve bayes and the k-nearest neighbor algorithm shows that the attributes of the courses have the most influence on student graduation (Table 1)

Summary

Introduction

Accreditation is a form of evaluation or assessment of the quality and feasibility of a higher education institution or study program conducted by an organization or the National Accreditation Board for Higher Education (BANPT) [1]. One of the National Accreditation Board for Higher Education accreditation assessments is the percentage of on-time graduation for each program [1]. The percentage of graduation students on-time in college can be predicted with learning analytics. Learning analytics are starting to be used in higher education to improve the quality of education. It can provide benefits, namely increasing graduation, curriculum development, improving lecturer performance, time of admission after graduation, and increasing research in the field of education. One method that is often used in analytic learning is classification

Methods

Results

Conclusion