PREDIKSI HARGA BERAS IR-64 III MENGGUNAKAN ALGORITMA LONG SHORT TERM MEMORY (LSTM)

PUSPITA, INTAN MEGA (2021) PREDIKSI HARGA BERAS IR-64 III MENGGUNAKAN ALGORITMA LONG SHORT TERM MEMORY (LSTM). S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01.Cover+41519110127+INTANMEGAPUSPITA.pdf Download (686kB) | Preview
	Text (BAB I) 02.Bab 1+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (121kB)
	Text (BAB II) 03.Bab 2+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (188kB)
	Text (BAB III) 04.Bab 3+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (65kB)
	Text (BAB IV) 05.Bab 4+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (104kB)
	Text (BAB V) 06.Bab 5+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (112kB)
	Text (BAB VI) 07.Bab 6+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (188kB)
	Text (DAFTAR PUSTAKA) 08.Daftar Pustaka+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (76kB)
	Text (LAMPIRAN) 09.Lampiran+41519110127+INTANMEGAPUSPITA.pdf Restricted to Registered users only Download (175kB)

Abstract

Rice prices prediction is needed to actualize the stabilization of food prices. This is to achieve national food security. This study aims to predict rice prices at Perum BULOG by implementing the Long Short Term Memory (LSTM) algorithm using daily market price data for rice commodities of the IR-64 III in the DKI Jakarta area (Jatinegara, Pasar Minggu, and Kebayoran Lama) during the last 3 years (2018 to 2020). Methods to evaluate the performance of the algorithm model are Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results of model performance LSTM for each category dataset, ie for data categories Jatinegara Market has RMSE value of 2.82 and MAPE value of 3%, Kebayoran Lama Market has RMSE value of 1.68 and MAPE value of 2% and Minggu Market has RMSE value of 55.71 and MAPE value of 2% 11%. Keywords: long short term memory; lstm; time series; forecasting; price prediction Prediksi harga beras sangat diperlukan untuk mewujudkan stabilisasi harga pangan guna tercapainya ketahanan pangan nasional. Penelitian ini bertujuan untuk melakukan prediksi harga beras di Perum BULOG dengan mengimplementasikan algoritma Long Short Term Memory (LSTM) menggunakan data harga pasar harian komoditi beras yang berjenis IR-64 III di wilayah DKI Jakarta (Jatinegara, Pasar Minggu, dan Kebayoran Lama) selama periode 3 tahun terakhir (2018 s.d. 2020). Metode untuk mengevaluasi kinerja model algoritma pada penelitian ini adalah Root Mean Squared Error (RMSE) dan Mean Absolute Percentage Error (MAPE). Hasil kinerja model LSTM untuk masing-masing kategori dataset, yaitu untuk kategori data Pasar Jatinegara memiliki nilai RMSE sebesar 2.82 dan MAPE sebesar 3%, Pasar Kebayoran Lama memiliki nilai RMSE sebesar 1.68 dan MAPE sebesar 2% dan Pasar Minggu memiliki nilai RMSE sebesar 55.71 dan MAPE sebesar 11%. Kata kunci: long short term memory;lstm; time series; peramalan; prediksi harga

Item Type:	Thesis (S1)
NIM/NIDN Creators:	41519110127
Uncontrolled Keywords:	long short term memory;lstm; time series; peramalan; prediksi harga
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	Dede Muksin Lubis
Date Deposited:	26 Oct 2023 06:38
Last Modified:	26 Oct 2023 06:38
URI:	http://repository.mercubuana.ac.id/id/eprint/83350

Actions (login required)

View Item