Our novel approach utilizes proprietary spatial relational tools based upon GIS data combined with powerful machine learning algorithms to create risk prioritization models with rich depth. The results drive the decisions to provide the highest reduction in risk with economic evaluation, sorting through all the available attribute data and teasing out correlated features instead of relying on human intuition and experience, both of which can carry unintentional bias. The result is an output for the likelihood of an event that has much better statistical significance and predictive power than any traditional approach.