Skripsi

PEMODELAN PERAMALAN TINGKAT PENGANGGURAN DI INDONESIA MENGGUNAKAN ALGORITMA MACHINE LEARNING

---

Penilaian

---

Unemployment is a major global issue with significant socioeconomic impacts, including reduced individual well-being, increased inequality, and weakened economic stability. For Indonesia, as the largest economy in Southeast Asia, understanding the determinants of unemployment and developing reliable forecasting methods are crucial for effective policymaking. This study proposes a two-stage hybrid forecasting framework that integrates ARIMA forecasting to generate predictor variables, which are then applied as inputs to machine learning models. Using Indonesia’s long-term historical data from 1970 to 2023, the results show that the Gradient Boosting Regressor achieves the best performance, with a Mean Absolute Percentage Error (MAPE) of 14.7% on the 2023 holdout data. Feature importance analysis reveals that higher education, GDP growth, and foreign direct investment (FDI) are the most influential variables in predicting unemployment rates. Based on this framework, Indonesia’s unemployment rate is projected to undergo moderate fluctuations during 2024–2028

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507005652	T183881	T1838812025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1838812025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xviii, v-2.;ilus.;tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.31

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Machine Learning
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

NO

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment