Coastal areas all over the world are experiencing the effects of climate change. In particular, sea level rise, high storm surges, and intensive precipitation, are causing floods in these areas, resulting in excessive damage. Various academic studies and governmental projects have been studying the vulnerability of different systems, such as social systems, infrastructure systems, and ecosystems, to climate change effects. In particular, social vulnerability studies often use different social attributes (e.g., income and age), usually obtained from the US Census Bureau. Those can indicate whether a certain community is vulnerable to climate change effects. Hence, these attributes are considered to be indicators of social vulnerability and aggregating them into one value produces a social vulnerability index (SVI) that varies across geographical units. New packages in R (such as ACS), dramatically improve the efficiency of acquiring large capacity of data. Consequently, the analysis can be done for large scales and in fine resolutions. This feature, along with the use of dimensionality reduction methods (such as, Principal Component Analysis), and when combined with the use of table manipulation functions (such as within Data Table package), allow the automation of SVI’s construction in R. Consequently, the researcher can define the geography of interest, and quickly produce the relevant SVI. The current study uses the described algorithm to learn about social vulnerability to extreme flooding. In addition it uses statistical predictive models (such as regression and Structural Equation Modeling) to learn about the validity of SVIs and the weights (importance) of the various indicators.