Common practice in Machine Learning often implicitly assumes a stationary distribution, meaning that the distribution of a particular feature does not change over time. In practice, however, this assumption is often violated and real-world models have to be retrained as a result. It would be helpful, then, to be able to anticipate and plan for changes in distribution in order to avoid this retraining. Model Monitor is a Java toolkit that addresses this problem. It provides methods for detecting distribution shifts in data, comparing the performance of multiple classifiers under shifts in distribution, and evaluating the robustness of individual classifiers to distribution change. As such, it allows users to determine the best model (or models) for their data under a number of potential scenarios. Additionally, Model Monitor is fully integrated with the WEKA machine learning environment, so that a variety of commodity classifiers can be used if desired.