Robust Classification Systems for Imprecise Environments

In real-world environments, it is usually diicult to specify target operating conditions precisely. This uncertainty makes building robust classiication systems problematic. We show that it is possible to build a hybrid classiier that will perform at least as well as the best available classiier for any target conditions. This robust performance extends across a wide variety of comparison frameworks, including the optimization of metrics such as accuracy, expected cost, lift, precision , recall, and workforce utilization. In some cases, the performance of the hybrid can actually surpass that of the best known classiier. The hybrid is also eecient to build, to store, and to update. Finally, we provide empirical evidence that a robust hybrid clas-siier is needed for many real-world problems.