Skripsi

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

---

Penilaian

---

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%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507004137	T1787952	T1787952025	Central Library (REFERENCE)	Available but not for loan - Repaired

Detail Information

Series Title

-

Call Number

T1787952025

Publisher

Indralaya : Program Magister Ilmu Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvii, 117 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Ilmu Komputer

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment