PREDIKSI PENERIMA BEASISWA KARTU INDONESIA PINTAR KULIAH DENGAN HYBRID BACKPROPAGATION DAN PARTICLE SWARM OPTIMIZATION

NANDA, DIKA KURNIA and Rini, Dian Palupi (2025) PREDIKSI PENERIMA BEASISWA KARTU INDONESIA PINTAR KULIAH DENGAN HYBRID BACKPROPAGATION DAN PARTICLE SWARM OPTIMIZATION. Masters thesis, Sriwijaya University.

Preview	Image RAMA_55101_09012682327005_cover.jpeg.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (2MB) | Preview
	Text RAMA_55101_09012682327005.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (23MB) | Request a copy
	Text RAMA_55101_09012682327005_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_55101_09012682327005_0023027804_1_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_55101_09012682327005_0023027804_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (558kB) | Request a copy
	Text RAMA_55101_09012682327005_0023027804_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (379kB) | Request a copy
	Text RAMA_55101_09012682327005_0023027804_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (602kB) | Request a copy
	Text RAMA_55101_09012682327005_0023027804_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (213kB) | Request a copy
	Text RAMA_55101_09012682327005_0023027804_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (190kB) | Request a copy
	Text RAMA_55101_09012682327005_0023027804_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy

Abstract

The Indonesia Smart Card (KIP) College Program aims to improve the quality of human resources by providing educational assistance to students from underprivileged families. However, the distribution of KIP College in Palembang still faces problems, such as inaccuracy in targeting and a lack of public understanding of the program. The suboptimal selection process for scholarship recipients results in students who should be prioritized being overlooked. Additionally, decision-making takes a long time due to the numerous variables that must be considered and the lack of transparency in data processing. This study discusses the Backpropagation (BP) method for predicting KIP Kuliah scholarship recipients, which has previously been applied for classifying educational assistance recipients with high accuracy. However, BP has weaknesses such as the risk of local minima and long training times. To address this, the Particle Swarm Optimization (PSO) algorithm is used to optimize the weights of the BP neural network. PSO is a simple yet effective optimization algorithm for finding optimal weights more quickly and accurately. Previous research results indicate that combining BP with PSO can improve prediction accuracy compared to using BP alone. The research results indicate that the combination of these two methods produces a prediction model with high accuracy and strong relevance to the factors influencing scholarship recipient predictions using Backpropagation + Particle Swarm Optimization, outperforming the use of Backpropagation alone in its implementation. From the tests conducted, the best model architecture is the 2-5-1 model with an RMSE of 0.351 +/- 0.000 (an improvement of 0.037), where a smaller RMSE (Root Mean Squared Error) indicates a better model with an accuracy rate of 83.66667%.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Backpropagation (BP), Particle Swarm Optimazation (PSO), Model Prediksi, Kartu Indonesia Pintar (KIP)
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55101-Informatics (S2)
Depositing User:	Dika Kurnia Nanda
Date Deposited:	17 Jul 2025 01:44
Last Modified:	17 Jul 2025 01:44
URI:	http://repository.unsri.ac.id/id/eprint/178795

Actions (login required)

View Item