PREDIKSI HARGA CABAI MERAH DI PROVINSI BANTEN MENGGUNAKAN ALGORITMA LONG-SHORT TERM MEMORY

RIANTO, RENDY AKBAR (2024) PREDIKSI HARGA CABAI MERAH DI PROVINSI BANTEN MENGGUNAKAN ALGORITMA LONG-SHORT TERM MEMORY. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 COVER.pdf Download (531kB) | Preview
Preview	Text (ABSTRAK) 02 ABSTRAK.pdf Download (121kB) | Preview
	Text (BAB I) 03 BAB 1.pdf Restricted to Registered users only Download (99kB)
	Text (BAB II) 04 BAB 2.pdf Restricted to Registered users only Download (224kB)
	Text (BAB III) 05 BAB 3.pdf Restricted to Registered users only Download (148kB)
	Text (BAB IV) 06 BAB 4.pdf Restricted to Registered users only Download (315kB)
	Text (BAB V) 07 BAB 5.pdf Restricted to Registered users only Download (24kB)
	Text (DAFTAR PUSTAKA) 08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (93kB)
	Text (LAMPIRAN) 09 LAMPIRAN.pdf Restricted to Registered users only Download (239kB)

Abstract

Chili (Capsicum annuum L) is a horticultural commodity included in seasonal vegetable crops, divided into several types such as large red chili, curly red chili, and cayenne pepper which includes green and red cayenne pepper. Recently, Indonesia has experienced long droughts and drought, which has resulted in the price of food commodities, especially chilies, experiencing erratic changes. The fluctuation of chili prices is a challenge for the government and society. Research by Steven Sen et al. entitled “Comparison of Multilayer Perceptron (MLP) and Long Short Term Memory (LSTM) Methods in Rice Price Forecasting” and research by Rizki Mugi Setya Adi and Sudianto, “Prediction of Food Commodity Prices Using the Long-Short Term Memory (LSTM) Algorithm” show that the use of the LSTM algorithm is effective in predicting prices by producing low errors. LSTM was chosen because of its ability to handle non-linear learning and complex time series data. This research predicts the price of red chili using the Long Short-Term Memory (LSTM) method with several stages of the process, namely pre-processing, data normalization, training, and prediction. Evaluation of prediction results is done using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). Based on testing using daily data on red chili prices and weather from January 1, 2022 to December 31, 2023 in Banten Province, the LSTM method produces the smallest MSE value of 0.0010 and the smallest MAPE of 4.97% with the proportion of training and testing data of 90:10%, a sequence length of 60, and 100 epochs. Keywords: Chili, Price, Dry Season, Prediction, LSTM Cabai (Capsicum annuum L) merupakan komoditas hortikultura yang termasuk dalam tanaman sayuran semusim, terbagi menjadi beberapa jenis seperti cabai merah besar, cabai merah keriting, dan cabai rawit yang meliputi cabai rawit hijau dan merah. Akhir-akhir ini Indonesia mengalami kemarau panjang dan dilanda kekeringan yang mengakibatkan harga komoditas pangan khususnya cabai mengalami perubahan yang tidak menentu. Fluktuasi harga cabai tersebut menjadi tantangan tersendiri bagi pemerintah dan masyarakat. Penelitian Steven Sen, dkk. yang berjudul “Komparasi Metode Multilayer Perceptron (MLP) dan Long Short Term Memory (LSTM) dalam Peramalan Harga Beras” serta penelitian Rizki Mugi Setya Adi dan Sudianto, “Prediksi Harga Komoditas Pangan Menggunakan Algoritma Long-Short Term Memory (LSTM)” menunjukkan bahwa penggunaan algoritma LSTM efektif dalam memprediksi harga dengan menghasilkan error yang rendah. LSTM dipilih karena kemampuannya dalam menangani pembelajaran non-linier dan data time series yang kompleks. Penelitian ini melakukan prediksi harga cabai merah menggunakan metode Long Short-Term Memory (LSTM) dengan beberapa tahapan proses, yaitu pre-processing, normalisasi data, training, dan prediksi. Evaluasi hasil prediksi dilakukan menggunakan Mean Squared Error (MSE) dan Mean Absolute Percentage Error (MAPE). Berdasarkan pengujian menggunakan data harian harga cabai merah dan cuaca dari 1 Januari 2022 hingga 31 Desember 2023 di Provinsi Banten, metode LSTM menghasilkan nilai MSE terkecil sebesar 0.0010 dan MAPE terkecil sebesar 4.97% dengan proporsi data pelatihan dan pengujian sebesar 90:10%, sequence data sebanyak 60, dan jumlah epoch sebanyak 100. Kata Kunci: Cabai, Harga, Musim Kemarau, Prediksi, LSTM

Item Type:	Thesis (S1)
Call Number CD:	FIK/SI. 24 116
NIM/NIDN Creators:	41820010015
Uncontrolled Keywords:	Cabai, Harga, Musim Kemarau, Prediksi, LSTM
Subjects:	100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 153 Conscious Mental Process and Intelligence/Intelegensia, Kecerdasan Proses Intelektual dan Mental > 153.1 Memory and Learning/Memori dan Pembelajaran > 153.12 Memory/Memori 300 Social Science/Ilmu-ilmu Sosial > 380 Commerce, Communications, Transportation (Perdagangan, Komunikasi, Transportasi) > 381 Commerce, Trade/Perdagangan > 381.1 Retail Trade/Perdagangan Ritail, Pasar 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma
Divisions:	Fakultas Ilmu Komputer > Sistem Informasi
Depositing User:	khalimah
Date Deposited:	31 Jul 2024 02:59
Last Modified:	31 Jul 2024 02:59
URI:	http://repository.mercubuana.ac.id/id/eprint/89926

Actions (login required)

View Item