This research utilizes machine learning techniques to investigate the motivational factors that influence individuals to engage as occasional crowdshipping couriers within urban logistics. Amidst the expanding integration of the gig economy with traditional logistic frameworks, the study specifically identifies critical motivational, economic, and demographic variables impacting participation. Employing Gradient Boosting Machines (GBM) and K-Neighbors (KNN), the analysis rigorously quantifies the effect of various factors such as incentives, parcel sizes, and personal preferences on the decision to participate in crowdshipping activities. The findings from the quantitative models are enriched with qualitative data from interviews, offering deeper insights into the personal motivations and perceived barriers faced by potential couriers. This blend of data-driven analysis and narrative inquiry not only enhances understanding of the underlying motivations but also aids in devising more effective operational strategies for crowdshipping in urban environments. The outcomes of this study provide actionable insights for policymakers, urban planners, and businesses, paving the way for more efficient and socially integrated urban delivery systems.