Peramalan Harga Kebutuhan Pokok (Beras) Pasca Pandemi Covid-19 dengan Backpropagation Neural Network

Penulis

  • I Putu Oka Wisnawa Politeknik Negeri Bali, Bukit Jimbaran Kuta Selatan, Badung, Bali, Indonesia
  • I Made Sulastra Politeknik Negeri Bali, Bukit Jimbaran Kuta Selatan, Badung, Bali, Indonesia

DOI:

https://doi.org/10.17977/um068v3i12023p1-11

Kata Kunci:

artificial neural network, backpropagation neural network, peramalan

Abstrak

As an algorithm in Artificial Neural Networks, Backpropagation Neural Networks have relatively good reliability and have been tested in forecasting case studies or data classification. Therefore, this algorithm was tested against Indonesian economic indicators (such as inflation rate, gross domestic product, Bank Indonesia rate, Rupiah exchange rate against USD, and prevailing electricity rate), to forecast the price of basic necessities, especially rice which is the staple food of Indonesian people. In this study, the Backpropagation Neural Network is tested again through a series of observation schemes. The dataset used is post-Covid-19 data, which is a picture of Indonesia's economic growth in 2022 after the pandemic, which is also affected by the issue of global economic recession in 2023. This means that the challenge is how a Backpropagation Neural Network can prove its reliability on data that has relatively grown volatile. However, based on the observation scheme that has been designed and tested, it turns out that the Backpropagation Neural Network is still able to provide a relatively high accuracy value, as evidenced by the relatively low MSE value of 0.02896. Of course, with the note that the preprocessing method used, the number of hidden layers and the number of epochs determine the performance of the reliability of the Backpropagation Neural Network in forecasting.

Sebagai sebuah algoritma dalam Artificial Neural Network, Backpropagation Neural Network memiliki keandalan yang relatif baik dan teruji dalam studi kasus peramalan ataupun klasifikasi data. Oleh karena itu, algoritma ini diujikan terhadap indikator-indikator ekonomi Indonesia (seperti nilai inflasi, produk domestik bruto, Bank Indonesia rate, nilai tukar Rupiah terhadap USD, dan tarif listrik yang berlaku), untuk meramalkan harga kebutuhan pokok, khususnya beras yang merupakan bahan makanan pokok masyarakat Indonesia. Dalam penelitian ini, Backpropagation Neural Network kembali diuji melalui serangkaian skema observasi. Dataset yang digunakan adalah data pasca pandemi Covid-19, yang merupakan gambaran pertumbuhan ekonomi Indonesia pada tahun 2022 pasca pandemi, yang juga terdampak isu resesi ekonomi global pada 2023. Ini berarti tantangannya adalah tentang bagaimana Backpropagation Neural Network mampu membuktikan keandalannya atas data yang memiliki pertumbuhan yang relatif fluktuatif. Namun, berdasarkan skema observasi yang telah dirancang dan diujikan, ternyata Backpropagation Neural Network tetap mampu memberikan nilai akurasi yang relatif tinggi, yang dibuktikan oleh nilai MSE yang relatif rendah, yaitu sebesar 0.02896. Tentunya dengan catatan bahwa metode preprocessing yang digunakan, jumlah hidden layer dan jumlah epoch menentukan performa keandalan Backpropagation Neural Network dalam melakukan peramalan.

Referensi

Astuti, P. B., & Mahardhika, A. S. (2020). COVID-19: How Does It Impact to the Indonesian Economy? Jurnal Inovasi Ekonomi, 5(02). Retrieved 10 February 2023 from https://doi.org/10.22219/JIKO.V5I02.11751.

Badan Pusat Statistik. (n.d.). Retrieved 10 February 2023, from https://www.bps.go.id/subject/13/keuangan.html#subjekViewTab5.

Data Inflasi. (n.d.). Retrieved 10 February 2023, from https://www.bi.go.id/id/statistik/indikator/data-inflasi.aspx.

Guan, H., Dai, Z., Zhao, A., & He, J. (2018). A Novel Stock Forecasting Model based on High-Order-Fuzzy-Fluctuation Trends and Back Propagation Neural Network. PLOS ONE, 13(2), e0192366. Retrieved 10 February 2023 from https://doi.org/10.1371/JOURNAL.PONE.0192366.

Habir, M. T., & Wardana, W. (2020). COVID-19’s Impact on Indonesia’s Economy and Financial Markets. Retrieved 10 February 2023 from https://think-asia.org/handle/11540/12952.

Herliansyah, Y., Nugroho, L., Ardilla, D., & Putra, Y. (2020). The Determinants of Micro, Small and Medium Enterpreneur (MSME) Become Customer of Islamic Banks (Religion, Religiosity and Location of Islamic Banks). Retrieved 10 February 2023 from https://doi.org/10.4108/EAI.26-3-2019.2290775.

Nilai Tukar Mata Uang Asing Terhadap Rupiah | Satu Data Perdagangan. (n.d.). Retrieved 10 February 2023, from https://satudata.kemendag.go.id/data-informasi/perdagangan-dalam-negeri/nilai-tukar.

Peta Harga Barang Pokok | Satu Data Perdagangan. (n.d.). Retrieved 10 February 2023, from https://satudata.kemendag.go.id/data-informasi/harga-komoditas/peta-harga-barang-pokok.

Ping, F. F., & Fei, F. X. (2013). Multivariant Forecasting Mode of Guangdong Province Port throughput with Genetic Algorithms and Back Propagation Neural Network. Procedia - Social and Behavioral Sciences, 96, 1165–1174. Retrieved 10 February 2023 from https://doi.org/10.1016/J.SBSPRO.2013.08.133.

Produk Domestik Bruto (PDB) | Satu Data Perdagangan. (n.d.). Retrieved 10 February 2023, from https://satudata.kemendag.go.id/data-informasi/perdagangan-dalam-negeri/produk-domestik-bruto.

Raja Pramudita, M., Ruslina, E., Dewi,;, Gustini, R., & Fakultas, ; (2022). Resesi Ekonomi dan Implikasinya dari Perspektif Hukum Dagang Pasca Pandemi Tahun 2023. Nusantara: Jurnal Pendidikan, Seni, Sains Dan Sosial Humaniora, 1(01), 1–1. Retrieved 10 February 2023 from https://doi.org/10.11111/nusantara.xxxxxxx

Rayfinando, Y., Hutagaol, T., Keuangan, P., Stan, N., Putra, R., Sinurat, P., … Korespodensi, S. A. (2022). Strategi Penguatan Keuangan Negara Dalam Menghadapi Ancaman Resesi Global 2023 Melalui Green Economy. Jurnal Pajak Dan Keuangan Negara (PKN), 4(1S), 378–385. Retrieved 10 February 2023 from https://doi.org/10.31092/JPKN.V4I1S.1911.

Siregar, S. P., Wanto, A., Tunas, S., & Pematangsiantar, B. (2017). Analysis of Artificial Neural Network Accuracy Using Backpropagation Algorithm in Predicting Process (Forecasting). IJISTECH (International Journal of Information System and Technology), 1(1), 34–42. Retrieved 10 February 2023 from https://doi.org/10.30645/IJISTECH.V1I1.4.

Susilawati, S., Falefi, R., & Purwoko, A. (2020). Impact of COVID-19’s Pandemic on the Economy of Indonesia. Budapest International Research and Critics Institute-Journal (BIRCI-Journal), 3(2), 1147–1156. Retrieved 10 February 2023 from https://doi.org/10.33258/BIRCI.V3I2.954.

Tarif Adjustment. (n.d.). Retrieved 10 February 2023, from https://web.pln.co.id/pelanggan/tarif-tenaga-listrik/tariff-adjustment.

Diterbitkan

2023-01-26

Terbitan

Bagian

Articles