Exploration and evaluation of crowdsourced probe-based Waze traffic speed

Real-time traffic speed information is essential for effective traffic management. Due to the high costs of conventional data collection methods, transportation agencies have sought alternative data sources, such as Waze. To thoroughly evaluate and explore Waze, or similar probe-based traffic data, This study used a 10.8 mile stretch of I-40 in Knoxville, Tennessee to compare the speed measurements from Waze and Remote Traffic Microwave Sensors (RTMS) over a 2-month period. The main findings include: 1) The two independent datasets exhibit similar speed patterns and profiles with Waze speed values being slight higher than RTMS speeds under high-speed lower traffic conditions; the Waze speed values are more likely to be similar or even lower than RTMS speeds for low-speed near congestion conditions; 2) several factors affecting the speed differences between RTMS speeds and Waze speeds were identified, such as Waze speed value, time of day (peak vs. non-peak), AADT (Annual Average Daily Traffic), and segment length; and 3) Waze reported the same speed for several successive reporting periods if the real-time speed is not available. The effective Waze sampling period is about two to four minutes. Waze speeds had more real-time speed observations during congested times, indicating that Waze speeds are more reliable for congested scenarios. The findings lead to a better understanding of this source of data and the subsequent analysis results.