Hybrid SARIMA-ELM untuk Peramalan Jumlah Produksi Beras di Provinsi Jawa Timur

Pakpahan, Vera Febrianti (2025) Hybrid SARIMA-ELM untuk Peramalan Jumlah Produksi Beras di Provinsi Jawa Timur. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21083010054_Cover.pdf Download (686kB)
	Text (Bab 1) 21083010054_Bab 1.pdf Download (23kB)
	Text (Bab 2) 21083010054_Bab 2.pdf Restricted to Repository staff only until 2027. Download (379kB)
	Text (Bab 3) 21083010054_Bab 3.pdf Restricted to Repository staff only until 2027. Download (169kB)
	Text (Bab 4) 21083010054_Bab 4.pdf Restricted to Repository staff only until 2027. Download (5MB)
	Text (Bab 5) 21083010054_Bab 5.pdf Download (10kB)
	Text (Daftar Pustaka) 21083010054_Daftar Pustaka.pdf Download (155kB)
	Text (Lampiran) 21083010054_Lampiran.pdf Restricted to Repository staff only Download (230kB)

Abstract

This study examines the application of a hybrid Seasonal Autoregressive Integrated Moving Average (SARIMA) and Extreme Learning Machine (ELM) model for time series forecasting, with a case study on monthly rice production in East Java Province. The forecasting process was carried out in two stages: (1) building a SARIMA model to capture linear and seasonal patterns, and (2) processing the residuals from SARIMA predictions using ELM to detect non-linear patterns. The outputs from ELM were then combined with the SARIMA predictions to form the hybrid model. Model evaluation showed a Mean Absolute Percentage Error (MAPE) of 9,95% and a Root Mean Squared Error (RMSE) of 46.546,78, which indicates very good accuracy for time series forecasting. In addition to evaluation, this research also produced rice production projections for the period of January–March 2025, with predicted values of 151,916.53 tons, 202,587.71 tons, and 779,082.56 tons, respectively. This information can support stock management and distribution planning. As an additional contribution, a graphical user interface (GUI) was developed to enable users to access, visualize, and interpret the forecasting results more easily. The findings suggest that the SARIMA–ELM hybrid model is effective for forecasting time series data with both linear and non-linear patterns, and can be practically applied to support rice production and distribution planning.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Muhaimin, Amri	NIDN0023079502	amri.muhaimin.stat@upnjatim.ac.id
Thesis advisor	Saputra, Wahyu Syaifullah Jauharis	NIDN0725088601	wahyu.s.j.saputra.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Vera Febrianti Pakpahan

Date Deposited:

19 Sep 2025 03:26

Last Modified:

19 Sep 2025 03:26

URI:

https://repository.upnjatim.ac.id/id/eprint/43802