Predictive Modeling of Covid-19 Spread with Machine Learning: A Focus on Decision Tree Accuracy
Keywords:
Covid-19 Forecasting, Machine Learning Models, Decision Tree Accuracy, Predictive ModelingAbstract
Virus Sars CoV-2 merupakan penyebab utama wabah Covid-19 yang pertama kali terdeteksi di Wuhan, Tiongkok, pada Desember 2019 dan dengan cepat menyebar ke seluruh dunia. Penelitian ini bertujuan untuk memprediksi jumlah kasus terkonfirmasi dan tingkat keparahan wabah dalam rentang 23 Januari hingga 10 Juni 2020. Data yang digunakan adalah dataset terbuka dari Kaggle berjudul "Global Forecasting Covid-19 Week 5”. Untuk menghasilkan prediksi yang optimal, penelitian ini menguji berbagai algoritma pembelajaran mesin dan pembelajaran mendalam, yaitu Random Forest, XGBoost, Polynomial Regression, Decision Tree, ANN, dan LSTM. Kinerja model dinilai melalui skor dan Root Mean Square Error (RMSE). Hasil terbaik dicapai oleh model Decision Tree dengan skor sebesar 0,97 dan RMSE 52,57, menunjukkan akurasi tinggi dalam prediksi kasus Covid-19. Penelitian ini mengindikasikan bahwa model Decision Tree unggul dalam prediksi Covid-19 dibandingkan algoritma lain dan menawarkan potensi signifikan untuk pengembangan strategi mitigasi yang lebih efektif di masa mendatang.References
Balli S. (2021). Data Analysis of Covid-19 Pandemic and Short-term Cumulative Case Forecasting using Machine Learning Time Series Method. Chaos, Solitons, and Fractals 142:110512.
Fanelli, D. and Piazza, F. (2020). Analysis and Forecast of Covid-19 Spreading in China, Italy, and France. Chaos, Solitons, and Fractals 134:109761.
Yeshilkanat, CM. (2020). Spatio-temporal Estimation of the Daily Cases of Covid-19 in Worldwide using Random Forest Machine Learning Algorithm. Chaos, Solitons, and Fractals 140:110210.
Wang, J., Zhang, J., & Zhang, H. (2020). Logistic Models and Machine Learning for Covid-19 Prediction. International Journal of Environmental Research and Public Health, 17(8), 2905.
Ahmed, M., & Younis, M. (2020). Time Series Forecasting for Covid-19 Cases Using Deep Learning Algorithms. Journal of Computational Biology, 27(11), 1556-1568.
Sharma, A., & Rani, M. (2020). Deep Learning for Forecasting Covid-19 Spread. Journal of Machine Learning Research, 21(124), 1-15.
Zhang, Y., & Wang, M. (2020). Covid-19 Forecasting Using XGBoost and Machine Learning Models. Advances in Science, 15(3), 202-208.
Raj, A., & Gupta, A. (2020). Machine Learning Approaches for Epidemic Prediction. Computational Biology and Chemistry, 86, 107282.
Chen, M., & Zhao, Y. (2020). Predicting Epidemic Outbreaks Using Random Forest. International Journal of Environmental Research and Public Health, 17(1), 101.
Verma, A., & Gupta, D. (2020). Polynomial Regression for Modeling Covid-19 Growth. Mathematical Methods in the Applied Sciences, 43(6), 3211-3220.
Brown, G., & Maugis, S. (2020). Analyzing Covid-19 Trends with Machine Learning. The Lancet, 395(10223), 877-884.
Singh, D., & Kumar, S. (2020). AI in Public Health: Modeling and Predictions for Covid-19. Artificial Intelligence in Medicine, 105, 101864.
Wang, L., & Deng, X. (2020). AI-Assisted Epidemiological Forecasting for Covid-19. Journal of Epidemiology and Community Health, 74(10), 819-825.
Zhao, Z., & Zhang, T. (2020). Impact of Social Distancing on the Covid-19 Spread: A Machine Learning Study. Scientific Reports, 10, 21348.
Kumar, A., & Patil, A. (2020). Covid-19 Spread Forecasting Using AI Algorithms: A Comparative Study. Journal of Computational and Graphical Statistics, 29(3), 651-667.
