The rapid growth of urban populations in developing cities has intensified the need for sustainable and efficient transport solutions. However, despite the increasing adoption of micro-mobility services in the Philippines, behavioural and contextual determinants remain under investigated, creating a gap in understanding the factors that drive user adoption. This study explores a micro mobility marketplace by utilizing machine learning to estimate the likelihood of user adoption from behavioural and contextual conditions. Based on a structured survey distributed across the National Capital Region (NCR), collected survey data from 500 respondents were analyzed using machine learning algorithms. Results show that K-Nearest Neighbours outperformed the rest of the models, though XGBoost and Support Vector Machines also offered good results. Trust, attitude, and price value were the significantly high-ranking factors present in all the models and were the most important for decision-making. The study illustrates how the combination of behavioural understanding and machine learning can enhance user-centric services and encourages sustainable mobility service provision. These findings are relevant to service providers and policy makers seeking to upgrade urban transport infrastructure in fast-growing cities, particularly in the Philippines.