Funding source: LA Metro

Contract number: PS36665000

Funding amount: $316,808

Performance period: 3/15/18 to 6/30/21

Publications: https://doi.org/10.25554/8zte-1665

Link to full seminar video: https://www.youtube.com/watch?v=lLQTmV-Tzgg

Major events are a significant source of traffic congestion, especially in large metropolitan areas. We conduct a case study of football games played at the Los Angeles Memorial Coliseum, a venue located near downtown Los Angeles with a capacity of about 80,000. Two teams play home games at the Coliseum, the Los Angeles Rams and the University of Southern California Trojans. These events take place in an area that already has a high level of recurrent congestion. We analyze the impacts of game days by comparing game day traffic with traffic on control days on both the highway and arterial systems. Our data are speed records from in-road detectors. We estimate two sets of models to test relationships between game attributes and traffic performance. The first set are traditional regression models controlling for spatial and temporal correlation. The second set are Random Forest, a type of machine learning estimation. We find that Random Forest performs better, as it allows for complex nonlinearities in variables. Our results show that Rams and USC impacts are different. Rams fans arrive in a more concentrated time interval closer to start time of the games, and therefore have a greater impact on the major approach routes than USC fans. The greatest impacts on highways are around nearby freeway to freeway interchanges. Arterial traffic is more consistently affected with distance from the venue. The case study provides the basis for better management of major planned events.