To achieve the goal of encouraging more people to use sustainable modes of transportation, thereby reducing carbon emissions, it is necessary to understand the equitable distribution of active and shared transportation among demographic groups. This study investigated which individual and contextual factors influence perceptions of barriers to public transit, micromobility, and carpool. A non-parametric method (extreme gradient boosting decision tree) was employed to accurately model these relationships and rank the importance of the factors. To enhance model interpretability, Shapley Additive Explanations (SHAP) was employed to explain the model outcome. Three metropolitan U.S. regions—Greater Los Angeles, Greater Houston, and Virginia and Washington D.C.—were selected as the application regions for this developed methodology. Based on the findings, it was found that people who drive for most of their trips are more inclined to perceive the reliability of public transit as unsatisfactory and have a lack of familiarity with micromobility. Women are more prone to perceive public transit as unsafe, uncomfortable, and inaccessible, and minority groups are least likely to be unsatisfied with public transit, suggesting that they might be more willing to endure inadequate transportation service. Thus, ensuring that these groups feel that they have the right and ability to speak up about their experience and concerns is critical. This research provides insights for transportation agencies to develop equitable improvement and communication strategies for active and shared transportation systems, which is imperative for the widespread adoption of sustainable modes for all people regardless of demographic characteristics.