Abstract
Rice is one of the main commodities of trade in Indonesia. PT Food Station as the management company of Cipinang Rice Main Market every day publishes data on price, type of rice and the amount of rice that enters and exits Jakarta area. This study aims to forecast rice prices in the Jakarta area using data held by PT FoodStation during the 2016-2018 data period. Rice price prediction is carried out for the next 30 days using the Auto Regressive Integrated Moving Average (ARIMA) method on the Amazon Forecast and Amazon Sagemaker platforms. The ARIMA model is a form of regression analysis that measures the strength of one dependent variable that is relatively influential on other change variables. The ARIMA model is a special type of regression model in which the dependent variable is considered stationary and the independent variable is the lag or previous value of the dependent variable itself and the error lag. ARIMA is a combination of auto-regressive and moving average processes. The final result obtained in this experiment is that the ARIMA model on Amazon Sagemaker cloud computing is superior when compared to Amazon Forecast. From the experimental results obtained the results of Amazon Sagemaker RMSE (313.379941) are smaller than Amazon Forecast (322.4118029). So it can be concluded that the ARIMA model run at Amazon Sagemaker is more accurate than Amazon Forecast for forecasting the price of rice for 30 days at the Cipinang Rice Main Market
Highlights
Rice is one of the main commodities of trade in Indonesia
This study aims to forecast rice prices in the Jakarta area using data held by PT FoodStation during the 2016-2018 data period
“Peramalan harga beras IR64 kualitas III menggunakan metode Multi Layer Perceptron , Holt-Winters dan Auto Regressive Integrated Moving Average,” ULTIMATICS, vol XI, 2019
Summary
Pasar Induk Beras Cipinang (PIBC) merupakan sebuah pasar grosir yang menampung para pedagang besar dan dikelola oleh PT. Amazon Forecast menggunakan pembelajaran mesin didefinisikan sebagai: untuk menggabungkan data deret waktu dengan variabel tambahan untuk membuat peramalan Amazon SageMaker if d = 0: yt = Yt mencakup modul yang dapat digunakan bersama atau secara mandiri untuk membangun, melatih, dan if d = 1: yt = Yt − Yt−1 menerapkan model pembelajaran mesin. Ketika angka aktual dipasangkan ke dalam persamaan, Model ARIMA tersebut mengubah faktor-faktor tidak ada ambiguitas, tetapi penting untuk mengetahui pengaruh penyakit menjadi beberapa variabel waktu konvensi mana yang digunakan perangkat lunak ketika khusus dan kemudian mencocokkannya. Setelah User memberikan Untuk membantu memilih algoritma, Amazon data, Amazon Forecast akan secara otomatis SageMaker menyertakan 10 algoritma pembelajaran memeriksanya, mengidentifikasi apa yang bermakna, mesin paling umum yang telah diinstal sebelumnya dan dan menghasilkan model peramalan yang mampu dioptimalkan untuk menghasilkan hingga 10 kali lipat membuat prediksi hingga 50% lebih akurat daripada dari kinerja biasa. RMSE memiliki tujuan ganda: 1. Untuk berfungsi sebagai heuristik untuk model 2121 20160101 pelatihan
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
