Rancang Bangun Dashboard Peramalan Produksi Crude Palm Oil (CPO) di Indonesia Menggunakan Pendekatan Long Short Term Memory (LSTM)

Putra, Robi Ardana (2024) Rancang Bangun Dashboard Peramalan Produksi Crude Palm Oil (CPO) di Indonesia Menggunakan Pendekatan Long Short Term Memory (LSTM). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043211086-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (2MB) | Request a copy

Abstract

Sebagai produsen utama dalam pasar Crude Palm Oil (CPO) internasional, komoditas Crude Palm Oil (CPO) menjadi salah satu komoditas utama yang mendukung perekonomian Indonesia. Menurut data Badan Pusat Statistik (BPS) Crude Palm Oil (CPO) memberikan kontribusi yang besar dan konsisten terhadap nilai ekspor Indonesia. Oleh karena itu, produksi Crude Palm Oil (CPO) menjadi salah satu faktor potensial dalam perkembangan ekonomi negara. Produksi Crude Palm Oil (CPO)seringkali mengalami fluktuatif yang tinggi. Salah satu cara untuk menangani dan mengantisipasi risiko ini adalah dengan melakukan peramalan produksi Crude Palm Oil (CPO), dengan peramalan yang akurat, pemerintah dan pelaku industri dapat merencanakan kebijakan ekspor-impor yang lebih efektif, mengelola persediaan dan harga secara lebih stabil, serta menyesuaikan strategi investasi untuk mengurangi risiko ketidakpastian ekonomi dan memastikan kontribusi optimal sektor minyak kelapa sawit terhadap pertumbuhan ekonomi dan stabilitas negara. Penelitian ini bertujuan untuk meramalkan produksi Crude Palm Oil (CPO) di Indonesia menggunakan metode Long ShortTerm Memory (LSTM) dan mengimplementasikan hasilnya dalam bentuk dashboard interaktif. Penelitian ini menghasilkan bahwa karakteristik Crude Palm Oil (CPO) di Indonesia memiliki pola musiman, model Long Short-Term Memory (LSTM) menghasilkan nilai kriteria MAPE out sample dengan kriteria peramalan sangat baik, produksi Crude Palm Oil (CPO) di Indonesia diprediksi akan mengalami penurunan konstan, dan dashboard yang dirancang dapat melakukan peramalan terhadap data yang di upload pengguna.
=================================================================================================================================
As a major producer in the international Crude Palm Oil (CPO) market, Crude Palm Oil (CPO) is one of the main commodities that supports the Indonesian economy. According to data from the Central Statistics Agency (BPS), Crude Palm Oil (CPO) provides a large and consistent contribution to Indonesia's export value. Therefore, Crude Palm Oil (CPO) production is one of the potential factors in the country's economic development. Crude Palm Oil (CPO) production often experiences high fluctuations. One way to handle and anticipate this risk is to forecast Crude Palm Oil (CPO) production, with accurate forecasting, the government and industry players can plan more effective export-import policies, manage inventory and prices more stably, and adjust investment strategies to reduce the risk of economic uncertainty and ensure optimal contribution of the palm oil sector to economic growth and national stability. This study aims to forecast Crude Palm Oil (CPO) production in Indonesia using the Long Short-Term Memory (LSTM) method and implement the results in the form of an interactive dashboard. This study shows that the characteristics of Crude Palm Oil (CPO) in Indonesia have a seasonal pattern, the Long Short-Term Memory (LSTM) model produces an out sample MAPE criterion value with very good forecasting criteria, Crude Palm Oil (CPO) production in Indonesia is predicted to experience a constant decline, and the designed dashboard can forecast data uploaded by users.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Crude Palm Oil (CPO), Dashboard Interaktif, Long Short-Term Memory (LSTM), Interactive Dashboard
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA76.76.A63 Application program interfaces Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Robi Ardana Putra
Date Deposited:	31 Dec 2024 03:51
Last Modified:	31 Dec 2024 03:53
URI:	http://repository.its.ac.id/id/eprint/116064

Actions (login required)

View Item