Sasongko, Elisabeth Cheryl and Lumbantobing, Elfa Eukaristia Theresia (2024) Peramalan Sektor Lapangan Usaha Terbaik dan Produk Domestik Regional Bruto (PDRB) Harga Berlaku di Jawa Timur dengan Metode Feed Forward Neural Network (FFNN). Project Report. [s.n.], [s.l.]. (Unpublished)
![[thumbnail of 5006211054_5006211068-Project_Report.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5006211054_5006211068-Project_Report.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy |
Abstract
Penelitian ini bertujuan untuk menganalisis sektor lapangan usaha terbaik dan meramalkan Produk Domestik Regional Bruto (PDRB) harga berlaku Provinsi Jawa Timur secara triwulanan untuk lima tahun ke depan. Metode yang digunakan dalam penelitian ini adalah Feed Forward Neural Network (FFNN) dengan tahapan meliputi transformasi Box-Cox, uji stasioneritas Augmented Dickey-Fuller (ADF), analisis plot ACF dan PACF, serta seleksi variabel input menggunakan algoritma Random Forest. Hasil analisis menunjukkan bahwa sektor industri pengolahan merupakan sektor lapangan usaha dengan kontribusi terbesar terhadap PDRB Jawa Timur. Model FFNN yang dibentuk mampu memetakan pola historis PDRB dan menghasilkan proyeksi pertumbuhan yang konsisten dan positif hingga tahun 2029. Kesimpulan dari penelitian ini adalah bahwa pendekatan FFNN dapat digunakan secara efektif untuk meramalkan PDRB, serta pentingnya pemilihan sektor dan preprocessing data dalam membangun model prediksi deret waktu.
=====================================================================================================================================
This study aims to analyze the most prominent economic sector and forecast the Gross Regional Domestic Product (GRDP) at current prices for East Java Province on a quarterly basis for the next five years. The method employed is the Feed Forward Neural Network (FFNN), with stages including Box-Cox transformation, Augmented Dickey-Fuller (ADF) stationarity test, ACF and PACF analysis, and input variable selection using the Random Forest algorithm. The analysis results show that the manufacturing sector is the highest contributing sector to East Java’s GRDP. The constructed FFNN model is capable of capturing the historical GRDP patterns and produces consistent and positive growth projections through 2029. The study concludes that the FFNN approach is effective for GRDP forecasting and highlights the importance of sector selection and data preprocessing in building a reliable time series prediction model.
| Item Type: | Monograph (Project Report) |
|---|---|
| Uncontrolled Keywords: | PDRB, Peramalan, FFNN, Industri Pengolahan, GRDP, Forecasting, FFNN, Manufacturing. |
| Subjects: | H Social Sciences > HB Economic Theory > Economic forecasting--Mathematical models. |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis |
| Depositing User: | Elisabeth Cheryl Sasongko |
| Date Deposited: | 11 Jul 2025 06:39 |
| Last Modified: | 11 Jul 2025 06:39 |
| URI: | http://repository.its.ac.id/id/eprint/119569 |
Actions (login required)
 |
View Item |