What cities have is how people travel: Conceptualizing a data-mining-driven modal split framework

As city-level modal splits are outcomes of city functions, it is essential to understand whether and how attributes affect derive a shift toward low-emission travel modes sustainable mobility in cities. This study elucidates this relationship between 46 cities worldwide, proposing two-step data mining framework. First, using the K-Means method, we classify into private-vehicle-, public-transit-, bicycle-dominant groups based on their splits. Second, categorize environmental, socio-demographic, transportation planning factors quantify interlocked impacts cities' via decision tree method. We observe that socio-demographic factor has highest impact determining In addition, high population density employment rate positively associated with modes. High gasoline tax low public transit taxi fares often make people reconsider possessing private vehicles. On other hand, extreme weather conditions (e.g., hot temperatures) can prevent bicycle usage. Our contribution expands introduced policies for shifts real-world paradigm present implications proposed framework developing practical strategies.