components of a system by susceptibility to failure. In this extended abstract, we present an ongoing project to rank the underground primary feeders of Consolidated Edison Company of New York according to their susceptibility to outages. We describe our framework and the application of different machine learning ranking methods along with experiments on concept drift detection. Between the high-voltage transmission system and the household-voltage secondary system, electricity is sent through primary distribution feeders, cables which move energy around the New York city area. There are three regions of interest1