Forecasting Rice, Cooking Oil, and Egg Prices in CPI Areas of East Java Province Using a Hybrid ARIMA-LSTM Method

Nawwafi, Muhammad Zaki (2026) Forecasting Rice, Cooking Oil, and Egg Prices in CPI Areas of East Java Province Using a Hybrid ARIMA-LSTM Method. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010224-cover.pdf Download (1MB)
	Text (Bab 1) 21081010224-bab1.pdf Download (102kB)
	Text (Bab 2) 21081010224-bab2.pdf Restricted to Repository staff only until 17 June 2029. Download (617kB) \| Request a copy
	Text (Bab 3) 21081010224-bab3.pdf Restricted to Repository staff only until 17 June 2029. Download (762kB) \| Request a copy
	Text (Bab 4) 21081010224-bab4.pdf Restricted to Repository staff only until 17 June 2029. Download (5MB) \| Request a copy
	Text (Bab 5) 21081010224-bab5.pdf Download (91kB)
	Text (Daftar Pustaka) 21081010224-daftarpustaka.pdf Download (135kB)

Abstract

Price instability and fluctuations of basic commodities in East Java pose a serious challenge, affecting public purchasing power and complicating government efforts to control inflation. This study proposes a Hybrid ARIMA–LSTM method using a decomposition approach to improve short-term price forecasting accuracy. In this approach, daily time-series data from the 2015–2024 period are decomposed into three components: the trend component is modeled using ARIMA, while the seasonal and residual components are modeled using LSTM. The model was evaluated on medium rice, bulk cooking oil, and purebred chicken eggs across three regions: Surabaya, Banyuwangi, and Madiun. The experimental results demonstrate that the best parameter combinations were achieved through p and q orders between 0–3 for ARIMA, alongside adjusted unit architectures and learning rates for LSTM based on the specific data characteristics of each region. Overall, the Hybrid ARIMA–LSTM method proves effective and yields higher accuracy for forecasting basic commodity prices compared to single models, despite requiring greater computational time.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Wahanani, Henni Endah	NIDN0022097811	henniendah.if@upnjatim.ac.id
Thesis advisor	Sihananto, Andreas Nugroho	NIDN0012049005	andreas.nugroho.jarkom@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Muhammad Zaki Nawwafi

Date Deposited:

17 Jun 2026 07:54

Last Modified:

18 Jun 2026 01:35

URI:

https://repository.upnjatim.ac.id/id/eprint/54022