A Machine Learning Model for Estimating Street Level Travel Time Using GTFS FeatureS

It can be concluded that the proposed WBPST-SVR model presents a robust and accurate framework for street-level travel time estimation using GTFS features. By combining weighted spatio-temporal data Support Vector Regression, the approach effectively addresses the nonlinear, dynamic, and data-intensive nature of urban traffic systems. The approach combines the WBPST and the SVR models for data filtration and pattern recognition respectively. The model attains convergence in 68 iterations with an MAPE value of just 2.44% for parasitic travel time estimation clearly outperforming existing work in the domain of research.

[1]    S. Vlahogianni, M. Karlaftis, and J. Golias, "Short-term traffic forecasting: Where we are and where we’re going," Transportation Research Part C: Emerging Technologies, vol. 43, pp. 3–19, Jun. 2018. [2]    K. Tang et al., "Lane-level short-term travel speed prediction for urban expressways: An attentive spatio-temporal deep learning approach," IET Intelligent Transport Systems, vol. 18, no. 4, pp. 709–722, Apr. 2024. [3]    B. Yao et al., "A deep-learning framework considering multiple motifs for traffic travel time prediction," Proceedings of the Institution of Civil Engineers - Transport, May 2023. [4]    M. Afandizadeh et al., "Deep Learning Algorithms for Traffic Forecasting: A Comprehensive Review and Comparison with Classical Ones," Journal of Advanced Transportation, vol. 2024, Article ID 9981657, 2024. [5]    M. Li, D. Zhou, and S. Zhang, "The Application of Reinforcement Learning in Traffic Flow Prediction: Advantages, Problems, and Prospects," ITM Web of Conferences, vol. 70, 2025. [6]    Y. Lin et al., "Long-term Traffic Flow Prediction using Stochastic Configuration Networks for Smart Cities," IECE Transactions on Intelligent Systematics, vol. 1, no. 2, pp. 79–90, Sep. 2024. [7]    H. Yuan and G. Li, "A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation," Data Science and Engineering, Springer, vol. 6, pp. 63–85, Mar. 2021. [8]    C. Wu et al., "Spatiotemporal scenario generation of traffic flow based on LSTM-GAN," IEEE Access, vol. 8, pp. 186191–186198, 2020. [9]    L. Romo et al., "Short-Term Traffic Speed Prediction via Machine Learning," in Green, Pervasive, and Cloud Computing – GPC 2020 Workshops, Springer, Singapore, 2020, pp. 25–34. [10] M. Cao, V. O. Li, and V. W. Chan, "A CNN-LSTM model for traffic speed prediction," in 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), 2020, pp. 1–5.