A K-NEAREST ALGORITHM BASED APPLICATION TO PREDICT SNMPTN ACCEPTANCE FOR HIGH SCHOOL STUDENTS IN INDONESIA

WIBOWO, ADI TRI (2018) A K-NEAREST ALGORITHM BASED APPLICATION TO PREDICT SNMPTN ACCEPTANCE FOR HIGH SCHOOL STUDENTS IN INDONESIA. S1 thesis, Universitas Mercu Buana Jakarta.

[img] Text (JURNAL MAHASISWA)
Adi Tri Wibowo - A K-Nearest Algorithm Based Application to Predict SNMPTN Acceptance for High Sc.pdf
Restricted to Registered users only

Download (1MB)

Abstract

Abstract— Seleksi Nasional Masuk Perguruan Tinggi Negeri (SNMPTN) is one of the acceptances to enrol public universities which held simultaneously throughout Indonesia. In Indonesia, there is no application that can assist high schools in predicting the student acceptance to public universities yet. In this study, we propose an application that can predict SNMPTN results based on learning data. This prediction application will identify data-driven based on the SMAN 8 Jakarta alumni’s report cards accepted and not accepted in SNMPTN. The data is from the average scores within semesters 1 until 5 of alumni data as training data in the classification process. We compare the training data with two testing data models (training data itself and 10-folds cross validation) as testing data. The algorithm that is used for this study is K-Nearest Algorithm. The result shows that the optimal parameters to gain good prediction only involve 5 parameters, they are the average score of semester 1, the average score of semester 2, the average score of semester 3, the average score of semester 4, and the average score of semester 5. The results show good accuracy, 80% for evaluating the science majoring alumni’s data itself with K=3 and 89% for evaluating the social science majoring alumni’s data itself with K=3. The prediction is then applied in a web-based application which is developed utilizing the Relational Unified Process Framework. From this study we also find out that there are 5 out of 8 parameters that can be used in the SNMPTN prediction, they are average score in semester 1 until semester 5. Keywords— Seleksi Nasional Masuk Perguruan Tinggi Negeri (SNMPTN), Public University, Predicting, Classification, K-nearest Neighbour Algorithm

Item Type: Thesis (S1)
NIM: 41514010021
Uncontrolled Keywords: Seleksi Nasional Masuk Perguruan Tinggi Negeri (SNMPTN), Public University, Predicting, Classification, K-nearest Neighbour Algorithm
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 005 Computer Programmming, Programs, Data/Pemprograman Komputer, Program, Data > 005.5 General Purpose Application Programs/Program Aplikasi dengan Kegunaan Khusus
600 Technology/Teknologi > 650 Management, Public Relations, Business and Auxiliary Service/Manajemen, Hubungan Masyarakat, Bisnis dan Ilmu yang Berkaitan > 658 General Management/Manajemen Umum
600 Technology/Teknologi > 650 Management, Public Relations, Business and Auxiliary Service/Manajemen, Hubungan Masyarakat, Bisnis dan Ilmu yang Berkaitan > 658 General Management/Manajemen Umum > 658.01-658.09 [Management of Enterprises of Specific Sizes, Scopes, Forms; Data Processing]/[Pengelolaan Usaha dengan Ukuran, Lingkup, Bentuk Tertentu; Pengolahan Data] > 658.05 Data Processing Computer Applications/Pengolahan Data Aplikasi Komputer
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: Dede Muksin Lubis
Date Deposited: 09 Apr 2018 07:12
Last Modified: 17 Jul 2018 02:43
URI: http://repository.mercubuana.ac.id/id/eprint/41663

Actions (login required)

View Item View Item