“…In recent times, machine learning methods have gained significant popularity and are thus often used in this task as they can automatically learn the pattern of traffic dynamics. General practices include probabilistic graphical model (Antoniou, Koutsopoulos, & Yannis, ; Qi & Ishak, ; Zheng & Su, ) and k‐nearest neighbor method (Oh, Byon, & Yeo, ). To better capture the nonlinear relationship in the evolution of traffic (Smith & Demetsky, , ), the potential of neural networks was also investigated (e.g., Allström et al., ; Zhang, ).…”