Machine learning algorithms are gaining popularity in the hydrologic sciences. These algorithms often require tuning hyperparameters to tailor their performance to a specific purpose. Often these hyperparameters are selected based on prior assumptions or a single-objective optimization. However, these techniques fail to capture tradeoffs between type I (i.e., false positive) and type II (i.e., false negative) misclassifications which may have differing implications for many hydrologic applications. This presentation outlines a simple methodology to identify tradeoffs among multiple objectives describing misclassifications, including accuracy, area under the receiver operating characteristic curve, false positive rate, and true positive rate, on an illustrative classification problem. Applications of this methodology to broader hydrologic problems are also discussed. Authors: Jacob Kravits, Kyri Baker, Joseph Kasprzyk