Optimalisasi Prediksi Kasus COVID-19 di Indonesia: Perbandingan Teknik Validasi 80-20 Split dan Walk-Forward dengan ARIMA
DOI:
https://doi.org/10.32664/j-intech.v12i02.1373Kata Kunci:
80-20 split validation, ARIMA model, COVID-19 forecasting, epidemiological forecasting, Indonesia, walk-forward validationAbstrak
Penelitian ini menyajikan studi komparatif teknik validasi split 80-20 dan walk-forward dalam meramalkan kasus COVID-19 harian di Indonesia menggunakan model ARIMA. Berdasarkan kajian penelitian sebelumnya, model ARIMA telah terbukti efektif dalam berbagai konteks epidemiologi, namun studi ini menyoroti pentingnya pemilihan teknik validasi yang tepat. Penelitian ini menggunakan data dari tanggal 3 Januari 2020 hingga 18 Oktober 2023 untuk mengembangkan model prediktif yang kinerjanya diukur menggunakan Mean Absolute Error (MAE) dan Root Mean Squared Error (RMSE). Hasil penelitian menunjukkan bahwa teknik validasi walk-forward lebih unggul dibandingkan split 80-20, dengan MAE sebesar 137.32 dan RMSE sebesar 198.23, dibandingkan dengan MAE split 80-20 sebesar 4190.92 dan RMSE sebesar 4479.15. Temuan ini mengindikasikan bahwa validasi walk-forward memberikan prediksi yang lebih akurat dan dapat diandalkan untuk skenario data yang dinamis dan tidak stasioner. Studi ini menegaskan pengaruh signifikan dari pemilihan teknik validasi terhadap kinerja model ARIMA, memberikan kontribusi baru dalam metodologi peramalan epidemiologi.
Referensi
Aji, B. S., Indwiarti, & Rohmawati, A. A. (2021). Forecasting Number of COVID-19 Cases in Indonesia with ARIMA and ARIMAX Models. 2021 9th International Conference on Information and Communication Technology (ICoICT), 71–75. https://doi.org/10.1109/ICoICT52021.2021.9527453
Benvenuto, D., Giovanetti, M., Vassallo, L., Angeletti, S., & Ciccozzi, M. (2020). Application of the ARIMA model on the COVID-2019 epidemic dataset. Data in Brief, 29, 105340. https://doi.org/10.1016/j.dib.2020.105340
de Araújo Morais, L. R., & da Silva Gomes, G. S. (2022). Forecasting daily Covid-19 cases in the world with a hybrid ARIMA and neural network model. Applied Soft Computing, 126, 109315. https://doi.org/10.1016/j.asoc.2022.109315
Hasri, H., Mohd Aris, S. A., & Ahmad, R. (2023). Comparison of Auto ARIMA and Auto SARIMA Performance in COVID-19 Prediction. 2023 IEEE 2nd National Biomedical Engineering Conference (NBEC), 106–110. https://doi.org/10.1109/NBEC58134.2023.10352616
Ismail, L., Alhmoudi, S., & Alkatheri, S. (2020). Time Series Forecasting of COVID-19 Infections in United Arab Emirates using ARIMA. 2020 International Conference on Computational Science and Computational Intelligence (CSCI), 801–806. https://doi.org/10.1109/CSCI51800.2020.00150
Jin, Y.-C., Cao, Q., Wang, K.-N., Zhou, Y., Cao, Y.-P., & Wang, X.-Y. (2023). Prediction of COVID-19 Data Using Improved ARIMA-LSTM Hybrid Forecast Models. IEEE Access, 11, 67956–67967. https://doi.org/10.1109/ACCESS.2023.3291999
Mustafa, H. I., & Fareed, N. Y. (2020). COVID-19 Cases in Iraq; Forecasting Incidents Using Box - Jenkins ARIMA Model. 2020 2nd Al-Noor International Conference for Science and Technology (NICST), 22–26. https://doi.org/10.1109/NICST50904.2020.9280304
Pane, S. F., Adiwijaya, Sulistiyo, M. D., & Gozali, A. A. (2022). LSTM and ARIMA for Forecasting COVID-19 Positive and Mortality Cases in DKI Jakarta and West Java. 2022 Seventh International Conference on Informatics and Computing (ICIC), 1–6. https://doi.org/10.1109/ICIC56845.2022.10006959
Ratu, J. A., Masud, Md. A., Hossain, Md. M., & Samsuzzaman, Md. (2021). Forecasting the COVID-19 Pandemic in Bangladesh Using ARIMA Model. 2021 3rd International Conference on Sustainable Technologies for Industry 4.0 (STI), 1–6. https://doi.org/10.1109/STI53101.2021.9732576
Rob J Hyndman. (2018). Forecasting: principles and practice. OTexts.
Sahai, A. K., Rath, N., Sood, V., & Singh, M. P. (2020). ARIMA modelling & forecasting of COVID-19 in top five affected countries. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 14(5), 1419–1427. https://doi.org/10.1016/j.dsx.2020.07.042
Seabold, S., & Perktold, J. (2010). Statsmodels: Econometric and Statistical Modeling with Python. 92–96. https://doi.org/10.25080/Majora-92bf1922-011
Shi, Y., Wu, K., & Zhang, M. (2022). COVID-19 Pandemic Trend Prediction in America Using ARIMA Model. 2022 International Conference on Big Data, Information and Computer Network (BDICN), 72–79. https://doi.org/10.1109/BDICN55575.2022.00022
Singh, S., Mittal, S., & Singh, S. (2023). Analysis and Forecasting of COVID-19 Pandemic Using ARIMA Model. 2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS), 143–148. https://doi.org/10.1109/ACCESS57397.2023.10199278
Subagyo, A., Sunyoto, A., & Prasetio, A. B. (2022). Prediction of the Spread of Covid-19 in Indonesia Using the SEIRD Model and Hybrid Model with ARIMA Correction. 2022 1st International Conference on Smart Technology, Applied Informatics, and Engineering (APICS), 199–204. https://doi.org/10.1109/APICS56469.2022.9918765
