Article Sidebar

Submitted
November 12, 2025
Accepted
January 15, 2026
Published
January 16, 2026
Download
PDF
Statistic
Read Counter : 2 Download : 1

Main Article Content

Abstract

The increase in the volume of public complaints in urban areas requires an accurate and explainable decision support system. This study developed an Explainable Decision Support System (xDSS) based on the Extreme Gradient Boosting (XGBoost) algorithm combined with the SHapley Additive Explanations (SHAP) method to predict spatial and temporal trends in public complaints in DKI Jakarta Province. The research data was obtained from the Satu-Data Jakarta portal and included multi-year complaint reports that were processed through aggregation, temporal feature engineering, and regression-based metric evaluation. The results show that the XGBoost model has high predictive performance with an R² value of 0.8425, MAE of 2.9858, and RMSE of 4.9928, indicating the model’s ability to explain more than 84% of the variation in the actual number of complaints. SHAP analysis revealed that temporal features such as complaint_lag1 and complaint_ma3 had the most dominant influence, while external variables such as rainfall (rainfall_mm) and population density (population_density) also made positive contributions. These results indicate that the dynamics of public complaints are influenced by a combination of historical factors and environmental conditions. Practically, this xDSS system can provide accurate predictions and transparent interpretations, thereby supporting the implementation of Smart Governance and evidence-based policy. This approach strengthens the application of Explainable Artificial Intelligence (XAI) in public service governance by providing accurate, ethical, and auditable models to support strategic decision-making in the era of digital government.

Keywords

XGBoost SHAP Explainable AI Complaint Tren

Article Details

License

Copyright (c) 2026 Moeng Sakmar, Agus Darmawan, Puteri Awaliatus Shofo, Nurul Tiara Kadir

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite
Sakmar, M., Darmawan, A., Shofo, P. A., & Kadir, N. T. (2026). An Explainable Spatio-Temporal Decision Support System (DSS) Using XGBoost And SHAP For Urban Complaint Trend Prediction. Jurnal Sains, Nalar, Dan Aplikasi Teknologi Informasi, 5(1), 24–31. https://doi.org/10.20885/snati.v5.i1.44562
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX

References

  1. G. Kostopoulos, G. Davrazos, and S. Kotsiantis, “Explainable artificial intelligence-based decision support systems: A recent review,” Electronics, vol. 13, no. 14, p. 2842, 2024.
  2. S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” Adv. Neural Inf. Process. Syst., vol. 30, 2017.
  3. F. Yi et al., “XGBoost-SHAP-based interpretable diagnostic framework for alzheimer’s disease,” BMC Med. Inform. Decis. Mak., vol. 23, no. 1, p. 137, 2023.
  4. H. Lamane, L. Mouhir, R. Moussadek, B. Baghdad, O. Kisi, and A. El Bilali, “Interpreting machine learning models based on SHAP values in predicting suspended sediment concentration,” Int. J. Sediment Res., vol. 40, no. 1, pp. 91–107, 2025, doi: https://doi.org/10.1016/j.ijsrc.2024.10.002.
  5. G. Jin et al., “Spatio-temporal graph neural networks for predictive learning in urban computing: A survey,” IEEE Trans. Knowl. Data Eng., vol. 36, no. 10, pp. 5388–5408, 2023.
  6. Z. Liu, T. Felton, and A. Mostafavi, “Interpretable machine learning for predicting urban flash flood hotspots using intertwined land and built-environment features,” Comput. Environ. Urban Syst., vol. 110, p. 102096, 2024, doi: https://doi.org/10.1016/j.compenvurbsys.2024.102096.
  7. R. Madan and M. Ashok, “AI adoption and diffusion in public administration: A systematic literature review and future research agenda,” Gov. Inf. Q., vol. 40, no. 1, p. 101774, 2023, doi: https://doi.org/10.1016/j.giq.2022.101774.
  8. M. Saarela and S. Jauhiainen, “Comparison of feature importance measures as explanations for classification models,” SN Appl. Sci., vol. 3, no. 2, p. 272, 2021.
  9. S. Ergün, “Explaining XGBoost predictions with SHAP value: a comprehensive guide to interpreting decision tree-based models,” New Trends Comput. Sci., vol. 1, pp. 19–31, 2023, doi: 10.3846/ntcs.2023.17901.
  10. L. Jovanovic et al., “The explainable potential of coupling metaheuristics-optimized-xgboost and shap in revealing vocs’ environmental fate,” Atmosphere (Basel)., vol. 14, no. 1, p. 109, 2023.
  11. X. Fu et al., “An XGBoost-SHAP framework for identifying key drivers of urban flooding and developing targeted mitigation strategies,” Ecol. Indic., vol. 175, p. 113579, 2025, doi: https://doi.org/10.1016/j.ecolind.2025.113579.
  12. J. I. Hernandez, S. van Cranenburgh, M. de Bruin, M. Stok, and N. Mouter, “Using XGBoost and SHAP to explain citizens’ differences in policy support for reimposing COVID-19 measures in the Netherlands,” Qual. Quant., vol. 59, no. 1, pp. 381–409, 2025.
  13. X. Xu, X. Zhang, L. Qin, and R. Li, “Unveiling spatiotemporal evolution and driving factors of ecosystem service value: interpretable HGB-SHAP machine learning model,” Front. Environ. Sci., vol. 13, p. 1640840, 2025.
  14. M. Esperança, D. Freitas, P. V Paixão, T. A. Marcos, R. A. Martins, and J. C. Ferreira, “Proactive Complaint Management in Public Sector Informatics Using AI: A Semantic Pattern Recognition Framework.,” Appl. Sci., vol. 15, no. 12, 2025.
  15. S. Chen, Y. Zhang, B. Song, X. Du, and M. Guizani, “An intelligent government complaint prediction approach,” Big Data Res., vol. 30, p. 100336, 2022.
  16. J. I. Criado, R. Sandoval-Almazán, and J. R. Gil-Garcia, “Artificial intelligence and public administration: Understanding actors, governance, and policy from micro, meso, and macro perspectives,” Public Policy Adm., vol. 40, no. 2, pp. 173–184, 2025, doi: 10.1177/09520767241272921.
  17. S. Lee, J. Kang, and J. Kim, “Machine learning-based predictive model of ground subsidence risk using characteristics of underground pipelines in urban areas,” IEEE Access, vol. 11, pp. 69326–69336, 2023.
  18. S. Mukherjee and Z. Wei, “Suicide disparities across metropolitan areas in the US: A comparative assessment of socio-environmental factors using a data-driven predictive approach,” PLoS One, vol. 16, no. 11, p. e0258824, 2021.
  19. X. Jin, H. Ma, J.-Y. Xie, J. Kong, M. Deveci, and S. Kadry, “Ada-STGMAT: An Adaptive Spatio-Temporal Graph Multi-Attention Network for Intelligent Time Series Forecasting in Smart Cities,” Expert Syst. Appl., vol. 269, 2025, doi: 10.1016/j.eswa.2025.126428.
  20. M. Wang et al., “An XGBoost-SHAP approach to quantifying morphological impact on urban flooding susceptibility,” Ecol. Indic., vol. 156, p. 111137, 2023.
  21. Z. Xu, H. Zhang, A. Zhai, C. Kong, and J. Zhang, “Stacking Ensemble Learning and SHAP-Based Insights for Urban Air Quality Forecasting: Evidence from Shenyang and Global Implications,” Atmosphere (Basel)., vol. 16, no. 7, p. 776, 2025.
  22. Q. Liu and T. Hang, “Seasonal synergistic management of urban heat island effect and PM₂.₅ pollution: Insights from interpretable LightGBM-SHAP machine learning model,” Environ. Impact Assess. Rev., vol. 116, p. 108129, 2026, doi: https://doi.org/10.1016/j.eiar.2025.108129.
  23. Y. Ruan, X. Zhang, M. Zhang, F. Sun, and Q. Chen, “Nonlinear and synergistic effects of demographic characteristics on urban polycentric structure using SHAP.,” Sci. Rep., vol. 14, no. 1, p. 29861, Dec. 2024, doi: 10.1038/s41598-024-81076-9.
  24. Z. Li and Z. Zhan, “Model Selection and Evaluation for Learning Analytics via Interpretable Machine Learning,” in 2023 5th International Conference on Computer Science and Technologies in Education (CSTE), 2023, pp. 130–140.
  25. W. Yang, H. Li, J. Wang, and H. Ma, “Spatio-temporal feature interpretable model for air quality forecasting,” Ecol. Indic., vol. 167, p. 112609, 2024, doi: https://doi.org/10.1016/j.ecolind.2024.112609.
  26. A. Rahman et al., “Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities.,” AIMS public Heal., vol. 11, no. 1, pp. 58–109, 2024, doi: 10.3934/publichealth.2024004.
  27. N.-D. Hoang, T.-C. Huynh, and D.-T. Bui, “An interpretable machine learning framework for mapping hotspots and identifying their driving factors in urban environments during heat waves.,” Environ. Monit. Assess., vol. 197, no. 9, p. 1017, Aug. 2025, doi: 10.1007/s10661-025-14461-0.
  28. D. C. Saputra, D. P. Santosa, H. H. Sugasta, F. Adibah, and B. Rangga, “From Design to Execution: S-Curve-Controlled Implementation of a Hybrid Urban Drainage System in West Pontianak,” J. Tek. Sipil, vol. 25, no. 2, pp. 2084–2095, 2025.
  29. K. Zhang, B. Zhou, W. X. Zheng, and G.-R. Duan, “Finite-time stabilization of linear systems by bounded event-triggered and self-triggered control,” Inf. Sci. (Ny)., vol. 597, pp. 166–181, 2022.