Prediksi Jumlah Permintaan Darah UTD PMI Kota Pontianak Menggunakan ARIMA-Kalman Filter

Lyra Mauditia, Nurfitri Imro'ah, Wirda Andani

Abstract

Ensuring a sufficient supply of blood is a crucial aspect of providing health services. However, the large demand for blood is sometimes difficult to fulfill for one of the work units in the Indonesian Red Cross (PMI), namely the Blood Transfusion Unit. Therefore, blood demand prediction is needed to assist the blod transfuse unit in preparing sufficient blood stock. This study uses the ARIMA-Kalman Filter model to anticipate the quantity of blood demand for Blood Transfusion Unit PMI. The observations modeled in this study are daily observations of the amount of blood demand with the period January 1 to December 26, 2023 as an in-sample of 360 observations and blood demand for the period 27 to 31 December 2023 which amounted to 5 observations as an out-sample used to evaluate the model. The analysis’s findings indicate that the model obtained for predicting the amount of blood demand is the ARIMA (0,0,2) model, then the model parameters are estimated using Kalman Filter. The model used fulfills the diagnostic test and obtained a MAPE value of 15.021% in predicting out-sample data. Thus it can be concluded that the model used is in the very good category and is suitable for prediction. Furthermore, predictions are made for the next three days on the number of blood requests at Blood Transfusion Unit PMI Pontianak City to help health services prepare blood stocks for patients in need.

References

F. A. Yul, S. N. Meirizha, dan W. Laila, “Pengendalian persediaan darah dengan metode continuous review system pada Palang Merah Indonesia (PMI) Kota Pekanbaru,” Photon: Jurnal Sain dan Kesehatan, vol. 9, no. 2, hal. 49–57, 2019, doi: 10.37859/jp.v9i2.1119.

A. Rakhman dan A. Y. F. Sabanise, “Sistem informasi stok kebutuhan darah pada Palang Merah Indonesia metode moving average,” Jurnal Ilmiah Indonesia, vol. 4, no. 7, 2019.

A. Wanto dan A. P. Windarto, “Analisis prediksi indeks harga konsumen berdasarkan kelompok kesehatan dengan menggunakan metode backpropagation,” Jurnal & Penelitian Teknik Informatika Sinkron, vol. 2, no. 2, hal. 37–43, 2017, [Daring]. Tersedia pada: https://zenodo.org/record/1009223#.Wd7norlTbhQ

H. A. Maulana, “Pemodelan deret waktu dan peramalan curah hujan pada dua belas stasiun di Bogor,” Jurnal Matematika Statistika dan Komputasi, vol. 15, no. 1, hal. 50, 2018, doi: 10.20956/jmsk.v15i1.4424.

T. Kurniawan, L. Hanafi, dan E. Apriliani, “Penerapan metode filter kalman dalam perbaikan hasil prediksi cuaca dengan metode ARIMA,” Jurnal Sains Dan Seni ITS, vol. 3, no. 2, hal. 28–33, 2014, [Daring]. Tersedia pada: http://ejurnal.its.ac.id/index.php/sains_seni/article/view/7984

Sukarna, E. Y. P. Ananda, dan M. S. Wahyuni, “Rainfall forecasting model using ARIMA and Kalman Filter in Makassar, Indonesia,” Journal of Physics: Conference Series, vol. 2123, no. 1, 2021, doi: 10.1088/1742-6596/2123/1/012044.

R. Arviananta, S. Syuhada, dan A. Aditya, “Perbedaan jumlah eritrosit antara darah segar dan darah simpan,” Jurnal Ilmiah Kesehatan Sandi Husada, vol. 12, no. 2, hal. 686–694, 2020, doi: 10.35816/jiskh.v12i2.388.

I. H. Marysa dan A. W. Anggraita, “Studi pengaruh warna pada interior terhadap psikologis penggunanya, studi kasus pada unit transfusi darah Kota X,” JURNAL DESAIN INTERIOR, vol. 1, no. 1, hal. 41–50, 2016.

W. A. Mehta, Y. Sukmawaty, dan Khairullah, “Rainfall prediction climatological station of Banjarbaru using arima kalman filter,” Journal of Physics: Conference Series, vol. 2106, no. 1, 2021, doi: 10.1088/1742-6596/2106/1/012003.

H. Kusdarwati, U. Effendi, dan S. Handoyo, Analisis Deret Waktu Univariat Linier. Malang: UB Press Malang, 2022.

J. Hanke dan D. Wichern, “Business Forecasting Eight Edition,” New Jersey: Pearson Prenticehall., 2005.

N. W. Y. Cahyani, I. G. A. M. Srinadi, dan M. Susilawati, “Perbandingan transformasi Box-Cox,” E-Jurnal Matematika, vol. 4, no. 1, hal. 8–13, 2015.

W. W. Wei, “Time Series Analysis, Univariate and Multivariate Method Second Edition,” New York: Pearson Education., 2006.

N. M. Huda dan N. Imroah, Pengantar Analisis Deret Waktu Studi Kasus: Data Kalimantan Barat Dengan Aplikasi R. Pontianak: UNTAN PRESS, Pontianak, 2023.

G. Mokosolang, Y. A. R. Langi, dan M. L. Mananohas, “Prediksi harga saham Kimia Farma dan saham Netflix di era new normal menggunakan model autoregressive integrated moving average,” Jurnal Matematika dan Aplikasi, vol. 11, no. 1, hal. 23–31, 2022, [Daring]. Tersedia pada: https://ejournal.unsrat.ac.id/index.php/decartesian

F. L. Lewis, L. Xie, dan D. Popa, Optimal and Robust Estimation: With an Introduction to Stochastic Control Theory. CRC Press, 2008. doi: 10.1201/9781315221656.

D. J. Simon, “Kalman Filtering,” vol. 14, no. 6, hal. 72–79, 2001.

U. Khair, H. Fahmi, S. Al Hakim, dan R. Rahim, “Forecasting error calculation with mean absolute deviation and mean absolute percentage error,” Journal of Physics: Conference Series, 2017.

R. T. Prasetio, “Inventory control using statistics forecasting on manufacture company,” Jurnal Informatika, vol. 1, no. 2, hal. 136–142, 2014, doi: 10.31311/ji.v1i2.45.

DOI: https://doi.org/10.13057/ijas.v7i1.85958

Refbacks

  • There are currently no refbacks.