Abstract
Investigating the dynamics behind the likelihood of vehicle crashes has been a focal research point in the transportation safety field for many years. However, the abundance of data in today’s world generates opportunities for a deeper comprehension of the various parameters affecting crash frequency. This study incorporates data from many different sources including geocoded police-reported crash data, curbside infrastructure data, and socio-demographic data for the city of San Francisco, CA. Findings revealed that the GFMNB model provides a better statistical fit than the FMNB and NB models in terms of AIC and log-likelihood, while the NB model outperformed both mixture models in terms of BIC due to the model complexity of the latter. Among the significant variables, TNC pick-ups/dropoffs and duration of parked vehicles were positively associated with segment-level crashes.