PERBANDINGAN MODEL SUPPORT VECTOR REGRESSION, RANDOM FOREST REGRESSION, DAN RECURRENT NEURAL NETWORK DALAM MEMPREDIKSI HARGA CABAI (STUDI KASUS: PROVINSI SUMATERA SELATAN)

DESMARINA, SARAH and Meiriza, Allsela (2024) PERBANDINGAN MODEL SUPPORT VECTOR REGRESSION, RANDOM FOREST REGRESSION, DAN RECURRENT NEURAL NETWORK DALAM MEMPREDIKSI HARGA CABAI (STUDI KASUS: PROVINSI SUMATERA SELATAN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_57201_09031282126069.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_57201_09031282126069_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_57201_09031282126069_0013058302_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (759kB)
	Text RAMA_57201_09031282126069_0013058302_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (314kB) | Request a copy
	Text RAMA_57201_09031282126069_0013058302_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (68kB) | Request a copy
	Text RAMA_57201_09031282126069_0013058302_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (393kB) | Request a copy
	Text RAMA_57201_09031282126069_0013058302_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12kB) | Request a copy
	Text RAMA_57201_09031282126069_0013058302_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (165kB) | Request a copy
	Text RAMA_57201_09031282126069_0013058302_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Cabai adalah salah satu komoditas penyebab inflasi dan sangat vital bagi konsumsi masyarakat Indonesia. Di wilayah Sumatera Selatan, harga cabai seringkali tidak stabil sehingga dibutuhkan analisis prediksi harga cabai guna memitigasi dampak ketidakstabilan harga, terutama di Pasar Tradisional. Penelitian ini membandingkan tiga model penambangan data yaitu Support Vector Regression (SVR), Random Forest Regression (RFR), dan Recurrent Neural Network Long Short Term Memory (RNN LSTM) guna memutuskan model yang terbaik dalam prediksi harga cabai. Dataset mencakup 1240 harga berbagai jenis cabai di Pasar Tradisional Sumatera Selatan dengan memanfaatkan fitur lag dan musiman serta penerapan optimasi parameter guna peningkatan kinerja model. Hasil penelitian mengungkapkan bahwa SVR paling unggul dengan akurasi tertinggi (MAPE 0.03%-0.04% dan R2 0.90 0.94), stabilitas terbaik (MAE 1187.44-2478.49 dan MSE 11380618.92-16594596.73), waktu komputasi tercepat (23 detik), dan paling tahan melawan outlier. RFR juga berkinerja baik meskipun masih dibawah SVR. RNN LSTM mencatat hasil terendah di semua kategori. Penemuan ini mengkonfirmasi SVR sebagai model yang unggul dalam memprediksi harga cabai dan menyediakan insight berharga guna memitigasi risiko ketidakstabilan harga. Kata Kunci: Cabai, Data Mining, SVR, RFR, RNN LSTM

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Cabai, Data Mining, SVR, RFR, RNN LSTM
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 57201-Information Systems (S1)
Depositing User:	Sarah Desmarina
Date Deposited:	10 Jan 2025 03:55
Last Modified:	10 Jan 2025 03:55
URI:	http://repository.unsri.ac.id/id/eprint/163558

Actions (login required)

View Item