Data science is a computational discipline that addresses the problem of extracting knowledge from structured and unstructured data, including large datasets. One such large dataset provides insight into the speeds and categories of vehicles traveling the Zagreb-Karlovac section of the A1 highway over a period of 3 years, from 2018 to 2020. Additionally, meteorological data for the same section were recorded during the same period. The data include information such as: type and intensity of precipitation; air and road surface temperatures; freezing points of the road surface; visibility; thickness of the water layer; maximum wind speed; risk of ice formation, and the condition of the road surface. Each of these meteorological features, as well as the road condition features, affects the speed of vehicles on the observed section. Within this thesis, these influences will be visualized to determine which features have the greatest impact on vehicle speed. A model will be created using machine learning methods to select the meteorological and road condition features with the greatest influence on vehicle speed on the highway. Following this, an analysis will be conducted to correlate speed limit compliance with the selected features. The results will be appropriately visualized and interpreted in the context of potential interventions to increase compliance with speed limits under adverse conditions.