PENERAPAN METODE SUPPORT VECTOR REGRESSION UNTUK PREDIKSI PRODUKSI GULA AREN PADA KELOMPOK TANI SUMBER SEKAR LESTARI

Yunitasari, Masrema Alfiqiha (2025) PENERAPAN METODE SUPPORT VECTOR REGRESSION UNTUK PREDIKSI PRODUKSI GULA AREN PADA KELOMPOK TANI SUMBER SEKAR LESTARI. S1 thesis, Universitas Muhammadiyah Ponorogo.

	Text (SURAT PERSETUJUAN UNGGAH KARYA ILMIAH) 1 SURAT UNGGAH KARYA ILMIAH.pdf Download (604kB)
	Text (HALAMAN DEPAN) 2 HALAMAN DEPAN.pdf Download (5MB)
	Text (BAB I) 3 BAB I.pdf Download (242kB)
	Text (BAB II) 4 BAB II.pdf Restricted to Repository staff only Download (376kB) | Request a copy
	Text (BAB III) 5 BAB III.pdf Restricted to Repository staff only Download (650kB) | Request a copy
	Text (BAB IV) 6 BAB IV.pdf Restricted to Repository staff only Download (382kB) | Request a copy
	Text (BAB V) 7 BAB V.pdf Restricted to Repository staff only Download (207kB) | Request a copy
	Text (DAFTAR PUSTAKA) 8 DAFTAR PUSTAKA.pdf Download (203kB)
	Text (LAMPIRAN) 9 LAMPIRAN.pdf Restricted to Repository staff only Download (397kB) | Request a copy
	Text (SKRIPSI FULL TEXT) 10 SKRIPSI FULL TEXT.pdf Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

The increasing demand for palm sugar as a healthy natural sweetener highlights the need for an accurate production prediction system. The Sumber Sekar Lestari (SSL) farmer group in Ponorogo faces challenges in meeting market demand, which reaches 300–410 kg per month, as their production process still relies on traditional estimations. This study develops a prediction system based on Support Vector Regression (SVR) with an RBF kernel to forecast palm sugar production using market demand and the availability of sap (nira) as predictor variables. The choice of SVR is motivated by its ability to capture non-linear relationships between variables and produce precise predictions. The system was built by standardizing data and training the model using historical production records.

The testing results show that the system can predict production quantities with high accuracy, supported by features such as manual and batch data input, prediction visualization, and database storage. The findings demonstrate the effectiveness of the SVR model in modeling palm sugar production with parameters C=1.0, epsilon=0.1, and automatic gamma. For future development, it is recommended to perform hyperparameter optimization, include additional predictor variables such as weather conditions, and integrate the system with IoT for real-time raw material monitoring. This system is expected to help the farmer group plan production more effectively and efficiently.

Item Type:	Thesis (S1)
Uncontrolled Keywords:	palm sugar, production prediction, Support Vector Regression, production optimization
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Engineering
Depositing User:	Masrema Alfiqiha Yunitasari Masrema Alfiqiha Yunitasari
Date Deposited:	09 Sep 2025 06:00
Last Modified:	04 Nov 2025 02:28
URI:	https://eprints.umpo.ac.id/id/eprint/17827

Actions (login required)

View Item