Purwati, Neni and Nurlistiani, Rini and Devinsen, Oscar (2020) DATA MINING DENGAN ALGORITMA NEURAL NETWORK DAN VISUALISASI DATA UNTUK PREDIKSI KELULUSAN MAHASISWA. Jurnal Informatika, 20 (2).

[img] Text

Download (826kB)


Graduating on time is the desire of all students, and is one of the indicators in accreditation, namely the more number of students who graduate on time, the higher / better the score will be, so that graduation on time is an advantage for educational institutions. However, if the status of graduating students is not predicted early, it will result in many students graduating on time, and this will greatly harm students and educational institutions. This research was conducted using data from students who graduated for 4 years from 2016-2019. The classification method is an approach to grouping data in data mining, namely classifying data. The classification data mining method that will be used is the neural network algorithm. Neural network algorithms are used to predict student graduation which is difficult to do manually, while visualization is used to visually display recapitulation data so that it is more interesting and easy to understand. The attributes used in the training data consisted of Gender, Origin, Class, Department, Age, GPA, Judicium Date, Year of Judiciary and Result Class. There are 9 attributes that are parameterized, where 8 attributes are predictor and 1 attribute is result. Training and testing data by changing parameters, namely: Hidden Layer Size: 3, Training Time: 500, Learning Rate: 0.3, Momentum: 0.2 resulting in classification with 87.80% Precision, 86.90% Recall and Accuracy (accuracy level) of 92.83%. In addition, data visualization displays several reporting recapitulations in the form of a very complete dashboard, so that the prediction and visualization of the data can help in graduating students to be able to graduate on time, and provide recommendations for actions that must be taken appropriately by management or the authorities in making decisions

Item Type: Article
Subjects: Ilmu Komputer
Divisions: Jurnal > Jurnal Ilmu Komputer
Depositing User: Shela Safitri
Date Deposited: 02 Feb 2023 01:28
Last Modified: 02 Feb 2023 04:34

Actions (login required)

View Item View Item