PREDICTING URBAN TRAFFIC FLOW WITH CLASSICAL AND MACHINE LEARNING MODELS

Abstract

Urban traffic flow forecasting is essential for intelligent transportation management, particularly in data-constrained urban environments. This study presents a reproducible benchmark framework for hourly traffic flow prediction using the Metro Interstate Traffic Volume dataset, comprising 48,204 observations collected between 2012 and 2018 with weather and holiday attributes. To ensure methodological rigor, classical statistical approaches (Seasonal Naïve, AutoReg, and ARIMA/SARIMA) are compared with machine learning models, namely Random Forest and Long Short-Term Memory. A time-seriesaware validation strategy with chronological data partitioning is employed to prevent information leakage. Temporal, lagged, and rolling statistical features are generated exclusively from historical observations. Model performance is evaluated using Mean Absolute Error, Root Mean Square Error, Mean Absolute Percentage Error, and the coefficient of determination (R²). The study provides a transparent and reproducible comparison of forecasting approaches and discusses their applicability to developing urban transportation systems.