A Random Forest Regressor Mobility Framework for Traffic Management in a Smart Estate
DOI:
https://doi.org/10.62054/ijdm/0204.20Abstract
The increasing complexity of mobility within smart estates requires accurate predictive tools for proactive traffic management. Traditional reactive systems struggle to address dynamic traffic patterns, leading to congestion and delays. This study develops a Random Forest Regressor–based mobility framework that predicts traffic situations using multi-vehicle count data collected from an open-source dataset. The methodology includes data preprocessing, feature selection, an 80:20 train–test split, baseline Framework training, and hyperparameter tuning using GridSearchCV. The optimized Framework achieved improved performance, with accuracy increasing from 0.9950 to 0.9966 alongside gains in precision, recall, and F1-score. Future work will integrate real-time IoT sensor streams, weather and incident data, and comparisons with deep-learning Frameworks to enhance accuracy. The study contributes a practical, computationally efficient, and deployable ensemble-based traffic prediction framework tailored for smart-estate environments.
References
Chen, Y., Zhang, L., & Wang, H. (2021). Deep learning approaches for urban traffic flow prediction: A comprehensive review. Transportation Research Part C: Emerging Technologies, 128, 103199.
Feigon, S., & Murphy, C. (2018). Shared Mobility and the Transformation of Public Transit. Transportation Research Board.
Huang, X., Li, J., & Zhou, Y. (2018). Spatial interaction Frameworking for transportation networks: A distance-decay perspective. Journal of Transport Geography, 72, 174–183.
Jones, P. (2018). The evolution of urban transport policy: From rational planning to integrated sustainability. Urban Studies, 55(12), 2560–2578.
Kong, Q., Zhang, Y., & Ma, X. (2022). Comparative analysis of tree-based ensemble Frameworks and deep learning for short-term traffic prediction. Expert Systems with Applications, 187, 115913.
Kumar, S., Verma, A. K., & Mirza, A. (2024). Digital Transformation, Artificial Intelligence and Society: Opportunities and Challenges. Springer.
Rodrigue, J. P. (2018). The Geography of Transport Systems (4th ed.). Routledge.
Schultz, T. (2014). Community formation beyond geography: Shared identity and collective action. Sociological Review, 62(4), 745–761.
Vu, H., Shanks, K., & Phung, D. (2018). Understanding urban mobility patterns using social media data: A machine learning approach. Information Processing & Management, 54(3), 396–409.
Wang, M., Liu, D., & Chen, Z. (2018). Transportation revolutions: Historical developments and future perspectives. Transport Policy, 72, 1–9.
Williams, J., Smith, A., & Patel, R. (2023). Machine learning methods for traffic state prediction: A review. IEEE Transactions on Intelligent Transportation Systems, 24(6), 5342–5357.
Xu, H., Li, S., & Zhao, J. (2021). Rail-based urban transit and its impact on city development: A century-long review. Cities, 110, 103081.
Yu, H., Ma, X., & Zhu, Y. (2019). Taxi trajectory big data for urban mobility analysis and traffic forecasting. Sensors, 19(2), 432.
Yu, J., Wang, P., & Chen, X. (2020). Deep hybrid CNN-LSTM networks for traffic flow prediction. Neural Computing and Applications, 32(23), 17281–17293.
Yu, Y., Wang, T., & Chen, L. (2019). Spatial clustering of mobility flows using network-based community detection. Physica A: Statistical Mechanics and Its Applications, 531, 121759.
Yuan, M., & Mills, J. (2019). Detecting mobility patterns with Bluetooth sensing in urban environments. Sensors, 19(11), 2474.
Zhang, L., Li, Y., & Wu, X. (2018). Public transit smart-card data analytics for mobility pattern mining. Journal of Intelligent Transportation Systems, 22(6), 475–489.
Zhang, Q., Zhao, S., & Li, J. (2019). Paradigm enlargements in transportation policy: A systematic review. Transport Reviews, 39(1), 48–67.
Downloads
Published
Data Availability Statement
The primary dataset analyzed in this study was sourced from Kaggle, a publicly accessible online repository. All supplementary data generated during model development and evaluation are available from the corresponding author upon request.
Issue
Section
License
Copyright (c) 2025 Shuaibu S. Yelwa, Yusuf M. Malgwi (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors are solely responsible for obtaining permission to reproduce any copyrighted material contained in the manuscript as submitted. Any instance of possible prior publication in any form must be disclosed at the time the manuscript is submitted and a
copy or link to the publication must be provided.
The Journal articles are open access and are distributed under the terms of the Creative
Commons Attribution-NonCommercial-NoDerivs 4.0 IGO License, which permits use,
distribution, and reproduction in any medium, provided the original work is properly cited.
No modifications or commercial use of the articles are permitted.
