Prediksi Harga Komoditas Cabai Provinsi Jawa Timur Menggunakan Metode Support Vector Regression (SVR) dengan Optimasi Genetic Algorithm (GA)

Anggraini, Naomi Dwi (2026) Prediksi Harga Komoditas Cabai Provinsi Jawa Timur Menggunakan Metode Support Vector Regression (SVR) dengan Optimasi Genetic Algorithm (GA). Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21083010010_Cover.pdf Download (1MB)
	Text (Bab 1) 21083010010_Bab 1.pdf Download (328kB)
	Text (Bab 2) 21083010010_Bab 2.pdf Restricted to Repository staff only until 9 March 2029. Download (664kB)
	Text (Bab 3) 21083010010_Bab 3.pdf Restricted to Repository staff only until 9 March 2029. Download (397kB)
	Text (Bab 4) 21083010010_Bab 4.pdf Restricted to Repository staff only until 9 March 2029. Download (2MB)
	Text (Bab 5) 21083010010_Bab 5.pdf Download (276kB)
	Text (Daftar Pustaka) 21083010010_Daftarpustaka.pdf Download (197kB)
	Text (Lampiran) 21083010010_Lampiran.pdf Restricted to Repository staff only until 9 March 2029. Download (243kB)

Abstract

Chili is one of the horticultural commodities that has a significant influence on food price stability in East Java Province, which serves as a major production center and an area with high chili consumption. Fluctuations in chili prices create uncertainty that affects regional inflation and purchasing power. Therefore, a predictive model capable of generating accurate and stable price estimates is required. This study aims to develop a price prediction model for Bird’s Eye Chili, Large Red Chili, and Curly Red Chili using Support Vector Regression (SVR) optimized with a Genetic Algorithm (GA) to obtain optimal parameter combinations. The data used in this study consist of daily price data from January 2022 to October 2025. The research process includes data collection, preprocessing, and modeling using the SVR method optimized with a Genetic Algorithm. The optimization of parameters C, gamma, and epsilon was conducted to minimize prediction errors. The results indicate that the SVR-GA model provides better accuracy compared to SVR without optimization across all commodities. For Bird’s Eye Chili, the model achieved a MAPE of 1.45% and an RMSE of 1061.82; for Large Red Chili, a MAPE of 1.02% and an RMSE of 604.70; and for Curly Red Chili, a MAPE of 1.08% and an RMSE of 618.85. These relatively low error values demonstrate that the model is capable of capturing price movement patterns effectively. Furthermore, the developed model has been implemented in a streamlit-based interface to facilitate data analysis and visualization of prediction results. Keywords: Chili Price Prediction, Support Vector Regression (SVR), Genetic Algorithm (GA), Time Series, East Java

Item Type:

Thesis (Undergraduate)

Contributors:

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

Subjects:

H Social Sciences > HA Statistics
Q Science > Q Science (General)
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Naomi Dwi Anggraini

Date Deposited:

10 Mar 2026 01:26

Last Modified:

10 Mar 2026 01:26

URI:

https://repository.upnjatim.ac.id/id/eprint/50265