In the past decades, the United States of America and Canada have witnessed a continuous increase in the frequency and magnitude of climate change-induced natural disasters. These events include droughts, floods, wildfires, and most recently, tornadoes. In 2016, climate change induced damage was estimated to be $8.6 billion in Canada, while in the United States of America, floods are becoming one of the costliest and highest in occurrence of all climate change induced hazards, costing an average of $8 billion dollars annually. Also, hurricanes such as hurricane Sandy cost over $67 billion dollars of total damage, while more recently. hurricane Florence resulted in an estimated damage of $5 billion so far. It is thus clear that the effect of climate change is already costing North Americans billions of dollars annually, at an increasing rate. Coupled with climate change, the expansive developments of urban areas are causing a significant increase in flood-related disasters worldwide. However, most flood risk analysis and categorization efforts have been focused solely on the hydrologic features of flood hazards (e.g., inundation depth and duration) without considering the resulting long-term consequences in terms of losses and recovery time, and thus the community’s flood resilience. The aim of this study is to develop a flood resilience classification system at a community level that can be used in the development of disaster managerial insights and risk mitigation measures, to better prepare urban areas from future flood risks. This data-driven model will categorize communities using Machine learning classification techniques, bypassing the complexity and probabilistic nature of physics-based models.