Random Forest Based Traffic Congestion Classification in Pekanbaru, Indonesia
Keywords:
Traffic Congestion Classification, Random Forest, Traffic Flow Analysis, V/C Ratio, Decision Support SystemAbstract
Traffic congestion in Pekanbaru has become a critical urban challenge due to rapid growth in vehicle volume that is not matched by corresponding road capacity expansion. This study aims to develop a classification model that categorizes traffic congestion levels using original operational data obtained from the local Transportation Agency. The proposed approach employs a Random Forest classifier with three primary features: speed, traffic density, and the volume to capacity (V/C) ratio. Congestion levels are defined in three classes, low, moderate, and high, based on rule based thresholds derived from the Highway Capacity Manual (HCM) traffic engineering standards. The results demonstrate that the developed model achieves excellent predictive performance, reaching 98.86% accuracy on the testing dataset. Feature importance analysis further confirms that speed and the V/C ratio are the most dominant variables in determining congestion severity. Overall, the model is effective as a decision support tool for rapid identification of congestion hotspots and provides a practical foundation for developing a more responsive transportation management system in Pekanbaru
References
Ahmed, U., Tu, R., Xu, J., Amirjamshidi, G., Hatzopoulou, M., & Roorda, M. J. (2023). GPS based traffic conditions classification using machine learning approaches. Transportation Research Record, 2677(2), 1445 to 1454. https://doi.org/10.1177/03611981221111370
Akhtar, M., & Moridpour, S. (2021). A review of traffic congestion prediction using artificial intelligence. Journal of Advanced Transportation, 2021, 8878011. https://doi.org/10.1155/2021/8878011
Cvetek, D., Muštra, M., Jelušić, N., & Tišljarić, L. (2021). A survey of methods and technologies for congestion estimation based on multisource data fusion. Applied Sciences, 11(5), 2306. https://doi.org/10.3390/app11052306
Dong, J., Zhang, H., Cui, M., Lin, Y., Wu, H. Y., & Bi, C. (2024). TCEVis: Visual analytics of traffic congestion influencing factors based on explainable machine learning. Visual Informatics, 8(1), 56 to 66. https://doi.org/10.1016/j.visinf.2023.11.003
Hammoumi, A. E., Benabbou, L., & Himmi, M. M. (2025). Leveraging machine learning to predict traffic jams: A comparison of classification models and optimization methods. Results in Engineering, 25, 104241. https://doi.org/10.1016/j.rineng.2025.104241
Jha, M. K., Mishra, A., Saxena, S., & Verma, A. (2025). A machine learning approach to traffic congestion mapping and hotspot identification: A case study of two international cities. Future Transportation, 5(4), 161. https://doi.org/10.3390/futuretransp5040161
Leiser, N., & Yildirimoglu, M. (2021). Incorporating congestion patterns into spatio temporal deep learning algorithms. Transportmetrica B: Transport Dynamics, 9(1), 622 to 640. https://doi.org/10.1080/21680566.2021.1922320
Marazi, N. F., Panda, S., Katiyar, V., & Saha, P. (2023). Traffic congestion assessment tool for urban roads based on traffic and geometric characteristics: A case of Hyderabad, India. Journal of Transportation Engineering, Part B: Pavements, 149(4). https://doi.org/10.1061/JTEPBS.TEENG-7908
Muktar, M. N., Nagandla, S., & Sultana, S. (2025). Data driven modeling of traffic congestion to evaluate the effects of coordinated intersections. Transportation Engineering, 22, 100263. https://doi.org/10.1016/j.treng.2025.100263
Pan, S., Khateeb, Y., Zaidi, A. A., & Shakib, J. (2022). Incorporating traffic flow model into a deep learning algorithm for congestion estimation. Mathematical Problems in Engineering, 2022, 5926663. https://doi.org/10.1155/2022/5926663
Pang, L., Yue, H., Sun, C., & Zhao, J. (2023). Traffic congestion and urban air pollution: Evidence from Beijing. Journal of Environmental Economics and Management, 123, 102913. https://doi.org/10.1016/j.jeem.2023.102913
Seong, J., Kim, H., Kim, D., & Lee, J. (2023). Measuring traffic congestion with novel metrics: A case study of six US metropolitan areas. ISPRS International Journal of Geo Information, 12(3), 130. https://doi.org/10.3390/ijgi12030130
Shang, L., Zhong, L., Zhou, Y., & Shi, Y. (2024). Managing traffic congestion or improving air quality: Low emission zone policy as a multipurpose approach? Sustainable Cities and Society, 109, 105799. https://doi.org/10.1016/j.scs.2024.105799
Sokido, D. L., Worku, H., & Dulo, B. (2024). Measuring the level of urban traffic congestion for sustainable transportation in Addis Ababa, Ethiopia, the cases of selected intersections. Frontiers in Sustainable Cities, 6, 1366932. https://doi.org/10.3389/frsc.2024.1366932
Sun, Y., Jiang, G., Lam, S. K., & He, P. (2022). Learning traffic network embeddings for predicting congestion propagation. IEEE Transactions on Intelligent Transportation Systems, 23(8), 11591 to 11604. https://doi.org/10.1109/TITS.2021.3105445
Wu, X., Schaefer, A., Azevedo, I. L., & others. (2025). Best strategies for air quality and climate mitigation in road transport. Nature Communications, 16, 1714. https://doi.org/10.1038/s41467-025-56701-4
Xu, M., Wu, Y., Li, Y., & Jiang, Y. (2024). Personal mobility of employed residents reduces citywide traffic congestion: An empirical analysis based on public transport strike events. Science of the Total Environment, 943, 173164. https://doi.org/10.1016/j.scitotenv.2024.173164
