Skripsi

PREDIKSI HASIL SPMB JALUR TKA DENGAN PENDEKATAN ENSEMBLE LEARNING STACKING

---

The Seleksi Penerimaan Murid Baru (SPMB) through the Tes Kemampuan Akademik (TKA) pathway for senior high schools in Palembang is a competitive process that creates uncertainty in determining students’ admission chances. This study aims to develop a prediction model for student admission using a machine learning approach based on ensemble learning stacking. The dataset consists of 4,952 applicants from the 2025 TKA pathway. Data splitting is performed using Group Shuffle Split based on target schools to prevent data leakage, resulting in 3,649 training data and 1,303 testing data. The features include selection scores, school cutoff values, log-transformed distance, and school capacity. The results show that stacking with a single base learner (SVM) achieves the highest accuracy of 0.915. Meanwhile, stacking with two base learners (SVM and Random Forest) achieves the highest F1-score of 0.808 and demonstrates the most stable performance. The three base learner model yields an F1-score of 0.799. Overall, the stacking approach is effective in producing stable and balanced predictions of student admission outcomes.

---

Availability

Detail Information

Series Title

-

Call Number

T1959792026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xiii, 24 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem Rekomendasi
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment