IOP Conference Series: Materials

Science and Engineering

PAPER • OPEN ACCESS You may also like

- Optimal-arrangement-based four-
Prediction of student graduation accuracy using scanning-heads error separation
technique for self-calibration of angle
decision tree with application of genetic algorithms encoders
Yang Jiao, Ye Ding, Zeguang Dong et al.

- Capabilities and limitations of the self-

To cite this article: A Maulana 2021 IOP Conf. Ser.: Mater. Sci. Eng. 1073 012055 calibration of angle encoders
Ralf D Geckeler, Alfred Link, Michael
Krause et al.

- Assessing outdoor comfort near

graduation towers: An experimental
View the article online for updates and enhancements. calibration study in a public open space
F Görgen and M Rossi-Schwarzenbeck

This content was downloaded from IP address 114.10.101.137 on 28/02/2024 at 20:34

ATASEC 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1073 (2021) 012055 doi:10.1088/1757-899X/1073/1/012055

Prediction of student graduation accuracy using decision tree

with application of genetic algorithms

A Maulana*
Department of Telecommunications, Semarang State Polytechnic, Indonesia

*lana_ooh@ymail.com

Abstract. Many of students who can’t complete the study promptly is a problem that needs to
be faced with a fast and effective way. In the student's education system is an important asset to
the note the graduation rate of students promptly. Predicting graduation is very important for the
institution to determine the strategic policies for the institution. The scope of the study is limited
in performing accurate comparison between studies that only use Genetic Algorithm method and
the research-based Genetic Algorithm using forward selection. Here we can conclude that the
value of the highest accuracy is there in the Genetic Algorithm-based method Forward selection.
Thus the Genetic Algorithm method with the selection of attribute-based Forward Selection is
the best method for solving a problem in the prediction accuracy of graduation.

1. Introduction
The Graduation is one of the assessment items in the college accreditation process. The assessment
elements for graduates in a university will refer to the national standard SNPT for higher education
PERMEN DIKBUT number 3 of 2020. So that if students graduate academically on time it will help
assess the accreditation of a college. Graduating on time is very important and this is a priority policy
issue, even the passing rate is considered one of the institutional effectiveness [1].
The value of graduate accreditation plays an important role in accreditation, so every university tries
to make various efforts so that its students can graduate on time.
The Diploma (D3) education level is included in the scope of higher education, which is one
of the basic requirements in finding a job, where universities will prepare qualified and skilled
undergraduate candidates who have skills in their fields. Of course, in achieving the degree in
the Associate Expert (AMD) field, it takes a normal time for 3 years [2].

2. Literature review
Verry Riyanto, Abdul Hamid, Ridwansyah 2019 “Prediction of Student Graduation Time Using the Best
Algorithm” The results were obtained from the study of academic achievement during the study period,
architecture, and appropriate weights of the NN, DT, and SVM methods [3]. Of the three models tested
and experimented with, the highest value was SVM 85.18% to occupy the second position with a value
of 84.96% occupied by DT, and the smallest accuracy value was NN with a value of 84.68%.
Joseph Stephen Bassi, Emmanuel Gbenga Dada, Alkali Abdulkadir Hamidu and Mshelia Dauda
Elijah 2019 “Students Graduation on Time Prediction Model Using Artificial Neural Network” The
results showed that artificial neural networks are a promising tool [4].

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd 1
ATASEC 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1073 (2021) 012055 doi:10.1088/1757-899X/1073/1/012055

Agus Romadhona, Suprapedi, H. Himawan, 2017 “Timely student graduation prediction by age,
gender, and achievement index using decision tree algorithm” From this research, it was found that the
prediction of students who entered the study period of students who entered was influenced by age,
gender, GPA semester 1 to GPA 4 semesters, and the most influential was the 4th-semester student GPA
on time with a gain value of 0.340 from all attributes [5].
Susi Mashlahah 2013 “Prediction of student graduation uses the decision tree method with the
application of the C4.5 algorithm” The more sample data used, the greater the correctness of the
prediction [6].
Eko Prasetiyo Rohmawan, 2018 “Predicting student graduation on time uses the decision tree and
artificial neural network methods” The use of data mining with the Decision Tree method has an
accuracy of 74.51% and an Artificial Neural Network has a higher accuracy of 79.74% which can be
applied in predicting student graduation on time [7].

3. Research methods

3.1. Research purposes

In this study, the data used were data from students of the D-3 Computer Engineering Study Program,
Harapan Bersama Polytechnic of Tegal, the purpose of this study was to find and find the best algorithm
patterns with student data objects based on several determining variables to get the level of accuracy in
predicting graduate accuracy students using the Decision Tree method and research that will be carried
out with the Application of Genetic Algorithms.
The data in this study were taken from graduation data in 2019 as many as 306 students with initial
Nim attributes, gender, marital status, occupational status, social studies scores 1 to 4 occupation, and
parents' income. The research stages are as follows:

data collection

data
grouping processing

The Experimental and

proposed testing methods
method

Evaluation and results accuracy

Figure 1. Research stages.

3.2. Testing phase

The research was conducted using the decision tree method with the application of genetic algorithms,
the object of research taken from students of the D-3 Computer Engineering Study Program at the

2
ATASEC 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1073 (2021) 012055 doi:10.1088/1757-899X/1073/1/012055

Harapan Bersama Polytechnic Year 2016 in the form of data from Microsoft Excel then transformed
into the Rapid Miner tool by doing 10 fold cross-validation to get one prediction about the student's on-
time graduation to get the best accuracy rate results. As shown in the table below:

Table 1. Table of Attributes of data for graduates of the Harapan Bersama Tegal Polytechnic.

Atribut Information
NIM Student ID Number
Gender Gender
Marital status Marital status
Job Status Students or parents with Working or not working status
Income Total rupiah
IPS1 Semester Achievement Index 1
IPS2 Semester Achievement Index 2
IPS3 Semester Achievement Index 3
IPS4 Semester Achievement Index 4
Label 1. Be on time
Not on time

Figure 2. Decision Tree Model of student graduation data.

From the Decision Tree in Figure 2. obtained rules for predicting student graduation data on time or not
on time. By using the Decision Tree Algorithm, so that you get a rule that will be used for decision
making on new data.
In conducting classification, this method can be evaluated based on criteria such as the level of
accuracy, speed, reliability, scalability, and interpretability. Then after the data is processed, the level of
accuracy can be tested to see the performance of the Decision Tree algorithm
From the results of testing the data for graduate students in 2019 above, it is evident that the test
results of the Decision Tree Algorithm method have a high accuracy value.

3
ATASEC 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 1073 (2021) 012055 doi:10.1088/1757-899X/1073/1/012055

4. Conclusion
Based on the results of the data accuracy analysis, the graduation data of the students of the Harapan
Bersama Tegal Polytechnic using the Decision Tree with the Genetic Algorithm Application to predict
student graduation. The resulting model can determine the best method in predicting student graduation.

References
[1] Depkumham 2010 Peraturan pemerintah RI no 66 Tentang Perubahan atas peraturan
Pemerintah no 17 tahun 2010 tentang pengolahan dan penyelenggaraan pendidikan
www.djpp.depkumham.go.id, Jakarta
[2] Mashlahah S 2013 Prediksi kelulusan mahasiswa menggunakan metode decision tree dengan
penerapan algoritma C4. 5
[3] Riyanto V, Hamid A and Ridwansyah R 2019 Prediction of Student Graduation Time Using the
Best Algorithm Indones. J. Artif. Intell. Data Min. 2 1–9
[4] Bassi J S, Dada E G, Hamidu A A and Elijah M D 2019 Students Graduation on Time Prediction
Model Using Artificial Neural Network IOSR J. Comput. Eng. 21 28–35
[5] Romadhona A, Suprapedi S and Himawan H 2017 Prediksi Kelulusan Mahasiswa Tepat Waktu
Berdasarkan Usia, Jenis Kelamin, Dan Indeks Prestasi Menggunakan Algoritma Decision Tree
Cyberku J. 13 8
[6] Mashlahah S, Yaqin M A and Faisal M 2013 Prediction of Students Graduation Using Decision
Tree Method with the Implementation of Algorithm C4. 5 IEESE Int. J. Sci. Technol. 2 1
[7] Rohmawan E P 2018 Prediksi Kelulusan Mahasiswa Tepat Waktu Menggunakan Metode
Desicion Tree Dan Artificial Neural Network J. Ilm. Matrik 20 21–30