<p>Urban flooding is a devastating global natural disaster requiring robust risk assessment. Traditional methods often struggle with presence-only data (locations where floods occurred, without data on non-flood locations) and clear risk level classification. This study introduces an innovative integrated framework for urban flood risk analysis in Harbin, China, combining Maximum Entropy (MaxEnt) modeling, which excels with presence-only data, with Cloud Model theory for improved risk classification. Methodologically, our framework incorporates: (1) MaxEnt modeling using various environmental and socioeconomic factors; (2) spatial autocorrelation analysis to understand flood distribution; (3) Cloud Model theory implementation, which transforms probability values into linguistic risk levels while representing the uncertainty and fuzziness in these transitions; and (4) a comparative evaluation against other machine learning models. Key findings reveal that the MaxEnt model demonstrated strong predictive performance (AUC = 0.871), comparable to other approaches, despite only needing flood presence data. Human-related factors contributed over half of the total influence on flood risk. Clay loam soil showed the highest flood probability. Spatial analysis identified significant clustering of flood events in low-lying urban areas with inadequate drainage. The Cloud Model classification effectively translated flood probabilities into five risk levels, highlighting that low-risk areas predominate in peripheral high-elevation districts, while high-risk areas are concentrated in Harbin's urban core. This pioneering integration of MaxEnt with Cloud Model theory offers a robust methodology for urban flood risk assessment. The implications include providing a more nuanced, data-driven yet expert-knowledge-informed basis for urban planning, infrastructure development, and emergency management in flood-prone regions.</p>