Subgroup discovery in labeled data is the task of discovering patterns in the description space of objects to find subsets of objects whose labels show an interesting distribution, for example the disproportionate representation of a label value. Discovering interesting subgroups in purely numerical data - attributes and target label - has received little attention so far. Usually, one uses discretization methods that lead to a loss of information and suboptimal results. We consider the discovery of an optimal subgroup according to an interestingness measure in purely numerical data. We leverage concepts of closures on interval patterns and advanced pruning techniques. The relevance of our algorithm is studied empirically and we briefly describe an application scenario to the optimization of plant growth in a controlled environment.