Faza, Alya Awalin Hadita (2025) Peramalan Harga Beras Kualitas Sedang di Provinsi Jawa Barat Menggunakan Metode Fuzzy Time Series. Other thesis, Institut Teknologi Sepuluh Nopember.
![]() |
Text
2043211022_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2025. Download (1MB) | Request a copy |
Abstract
Harga beras di Indonesia merupakan salah satu indikator penting dalam perekonomian, terutama karena beras merupakan makanan pokok bagi sebagian besar penduduk. Provinsi Jawa Barat, sebagai lumbung padi nasional atau salah satu daerah penghasil beras terbesar di Indonesia memiliki peranan penting dalam menjaga stabilitas harga beras nasional, oleh sebab itu, hal tersebut menjadi dasar dalam peramalan harga beras sebagai salah satu solusi dalam membantu pemerintah dan pelaku pasar dalam mengambil keputusan strategis. Dalam penelitian ini dilakukan peramalan menggunakan metode Fuzzy Time Series Chen karena kemampuannya dalam menangkap pola pergerakan data harga historis secara fleksibel, serta ketepatan peramalan yang dihasilkan tinggi. Data yang digunakan merupakan data historis harga beras kualitas sedang pada tingkat penggilingan di Provinsi Jawa Barat periode Januari 2014 – Desember 2023. Berdasarkan hasil analisis, pendekatan Autocorrelation Function (ACF) menunjukkan lag signifikan pada lag ke-1, lag ke-2, lag ke-3, dan lag ke-4 yang artinya harga beras saat ini memiliki pengaruh pada harga beras pada 1 hingga 4 bulan berikutnya. Tingkat akurasi peramalan data testing yang dihasilkan sangat baik, dengan nilai MAPE sebesar 1,96%, MAD sebesar 197,0191, serta RMSE sebesar 256,9094. Dengan tingkat kepercayaan 95%, peramalan harga beras pada periode Januari 2024 diprediksi sebesar Rp 9.970, kemudian mengalami penurunan harga beras pada bulan Februari 2024 hingga Desember 2025 yang bernilai konstan pada harga Rp 9.962.
=====================================================================================================================================
The price of rice in Indonesia is an important indicator in the economy, especially because rice is a staple food for the majority of the population. West Java Province, as a national rice granary or one of the largest rice producing regions in Indonesia, has an important role in maintaining the stability of national rice prices, therefore, this is the basis for forecasting rice prices as a solution to assist the government and market players in make strategic decisions. In this research, forecasting was carried out using Chen's Fuzzy Time Series method because of its ability to capture historical price data movement patterns flexibly, and the resulting forecasting accuracy is high. The data used is historical data on the price of medium quality rice at the milling level in West Java Province for the period January 2014 – December 2023. Based on the results of the analysis, the Autocorrelation Function (ACF) approach shows significant lags at the 1st lag, 2nd lag, and 2nd lag. -3, and the 4th lag, which means that the current price of rice has an influence on the price of rice in the next 1 to 4 months. The level of forecasting accuracy of the resulting testing data is very good, with a MAPE value of 1.96%, MAD of 197.0191, and RMSE of 256.9094. With a confidence level of 95%, the forecast for the price of rice in the January 2024 period is predicted to be IDR 9,970, then there will be a decrease in the price of rice from February 2024 to December 2025 which is constant at a price of IDR 9,962.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | Fuzzy Time Series, Harga Beras Kualitas Sedang, Jawa Barat, Penggilingan, Peramalan, Fuzzy Time Series, Price of Medium Quality Rice , West Java, Milling, Forecasting |
Subjects: | H Social Sciences > HA Statistics > HA30.3 Time-series analysis |
Divisions: | Faculty of Vocational > 49501-Business Statistics |
Depositing User: | Alya Awalin Hadita Faza |
Date Deposited: | 22 Jan 2025 04:09 |
Last Modified: | 22 Jan 2025 04:09 |
URI: | http://repository.its.ac.id/id/eprint/116582 |
Actions (login required)
![]() |
View Item |