Improving Dengue Case Prediction in Bandung City using Random Forest and SHAP on Climate Demographic Data
DOI:
https://doi.org/10.65780/bima.v1i2.10Keywords:
Dengue Fever, Random Forest, explainable AI (XAI), Bandung City, Feature EngineeringAbstract
Dengue Hemorrhagic Fever remains a major public health concern in urban areas of Indonesia, particularly in Bandung City, due to its fluctuating incidence and strong dependence on environmental and population factors. This study focuses on improving dengue case prediction by integrating climate and demographic data through systematic feature engineering and explainable machine learning based on the Random Forest algorithm. Historical dengue case data from Bandung City were used to develop and evaluate the proposed prediction model. The evaluation results show that the Random Forest model achieved an R² value of 0.9032 and an RMSE of 2.3748, indicating reliable predictive performance and good generalization capability. The applied feature engineering strategy effectively enhanced data representation by capturing temporal dynamics, case growth patterns, and interactions among climate variables. Furthermore, model interpretability was improved through the application of Explainable Artificial Intelligence using SHAP, which revealed that temporal features derived from previous dengue case trends were the most influential factors, followed by climate interaction variables. These findings demonstrate that the proposed approach improves prediction accuracy while providing transparent and epidemiologically meaningful insights to support data driven dengue early warning systems at the regional level.
Downloads
References
[1] Pemerintah Provinsi Jawa Barat, “Musim Hujan Tiba, Dinkes Kota Bandung Ajak Masyarakat Tanggap DHF,” Diskominfo Kota Bandung.
[2] Redaksi Radar Bandung, “Penurunan DHF 2025 Jadi yang Terendah, Pemkot Bandung Bersiap Hadapi Lonjakan 2026.”
[3] E. Abbasi, “Aedes aegypti and dengue: insights into transmission dynamics and viral lifecycle,” Epidemiol. Infect., vol. 153, p. e88, Aug. 2025, doi: 10.1017/S0950268825100320.
[4] “Dengue and severe dengue,” World Healt Organization.
[5] P. Prasad et al., “Influence of climatic factors on the life stages of Aedes mosquitoes and vectorial transmission: A review,” J. Vector Borne Dis., vol. 61, no. 2, pp. 158–166, Apr. 2024, doi: 10.4103/jvbd.jvbd_42_24.
[6] A. Kolimenakis et al., “The role of urbanisation in the spread of Aedes mosquitoes and the diseases they transmit—A systematic review,” PLoS Negl. Trop. Dis., vol. 15, no. 9, p. e0009631, Sep. 2021, doi: 10.1371/journal.pntd.0009631.
[7] M. Nasir et al., “Machine Learning Approach to Predict the Dengue Cases Based on Climate Factors,” Window of Health : Jurnal Kesehatan, pp. 203–214, May 2024, doi: 10.33096/woh.vi.1428.
[8] A. Risqa JL, A. Alhaq, and N. Nissa, “Dengue Modeling Using Multiple Regression in Bandar Lampung Province, Indonesia,” Symmetry & Sigma: Journal of Mathematical Structures and Statistical Patterns, vol. 1, no. 1, pp. 73–86, Jun. 2024, doi: 10.58989/symmerge.v1i1.11.
[9] C. Rudin, C. Chen, Z. Chen, H. Huang, L. Semenova, and C. Zhong, “Interpretable machine learning: Fundamental principles and 10 grand challenges,” Stat. Surv., vol. 16, no. none, Jan. 2022, doi: 10.1214/21-SS133.
[10] Z. Liu, Y. Wang, F. Feng, Y. Liu, Z. Li, and Y. Shan, “A DDoS Detection Method Based on Feature Engineering and Machine Learning in Software-Defined Networks,” Sensors, vol. 23, no. 13, p. 6176, Jul. 2023, doi: 10.3390/s23136176.
[11] Md. S. Rahman and Md. A. B. Shiddik, “Explainable artificial intelligence for predicting dengue outbreaks in Bangladesh using eco-climatic triggers,” Glob. Epidemiol., vol. 10, p. 100210, Dec. 2025, doi: 10.1016/j.gloepi.2025.100210.
[12] N. Tian et al., “Precision Prediction for Dengue Fever in Singapore: A Machine Learning Approach Incorporating Meteorological Data,” Trop. Med. Infect. Dis., vol. 9, no. 4, p. 72, Mar. 2024, doi: 10.3390/tropicalmed9040072.
[13] H. Maulana and A. Sekar Sari, “Instal : Jurnal Komputer Analysis of Dengue Fever Spread Prediction Using Ensemble Learning Approach with Xgboost and Random”, doi: 10.54209/jurnalinstall.v16i03.227.
[14] A. Saleh and R. Mukhtar, “Early Detection of Dengue Hemorrhagic Fever Using Patient Medical Data with Ensemble Learning Methods 1*,” Indonesian Journal of Artificial Intelligence and Data Mining (IJAIDM), vol. 8, no. 3, pp. 635–645, 2025, doi: 10.24014/ijaidm.v8i3.38088.
[15] S. Surbakti, Hayatunnufus, and T. Henny Febriana, “Prediction of Dengue Fever in Coastal Areas of North Sumatera (Kuala Namu and Belawan) With Random Forest and Support Vector Machine (SVM) Methods,” Data Science: Journal of Computing and Applied Informatics, vol. 7, no. 2, pp. 103–110, Jul. 2023, doi: 10.32734/jocai.v7.i2-14355.
[16] P. Probst, M. N. Wright, and A. Boulesteix, “Hyperparameters and tuning strategies for random forest,” WIREs Data Mining and Knowledge Discovery, vol. 9, no. 3, May 2019, doi: 10.1002/widm.1301.
[17] S.-W. Wang et al., “A case study on the application of a data-driven (XGBoost) approach on the environmental and socio-economic perspectives of agricultural groundwater management,” Agric. Water Manag., vol. 318, p. 109729, Sep. 2025, doi: 10.1016/j.agwat.2025.109729.
