<p>In this paper, the existence of a statistically significant relation between microscopic traffic variables that reflect the individual driving behavior with macroscopic traffic dynamics at network level is investigated. Empirical evidence and machine learning techniques are used, applied on a publicly available dataset of vehicle trajectories recorded using Unmanned Aerial Units in the city center of Athens, from which acceleration, speed and outflow information is extracted. The exploratory analysis conducted reveals that extremely high or extremely low average acceleration and deceleration values, as well as high heterogeneity of driving behavior, are related to adverse traffic conditions, while intermediate values are associated with optimal outflow. Furthermore, the regression analysis based on a simple yet powerful Random Forests model showed that the macroscopic outflow rate in the region of interest can be accurately predicted by the microscopic behavioral variables, such as acceleration. The further analysis of the strength of the developed relationships using Shapley additive explanations analysis, provided important insights regarding the influence of driving behavior on the observed outflow, validating the finding that aggressive or extremely cautious driving is connected with reduced traffic conditions. The specific findings can have far reaching implications for traffic management and Connected Cooperative Automated Mobility (CCAM), such as optimizing traffic conditions through controlling behavior, as well as more scalable simulation and an alternative perspective of observing traffic conditions.</p>