Machine-learning indirect test relies on powerful statistical algorithms to build prediction models that relate cheap measurements to costly performance metrics. Though many works in the past have been focused on proposing different models or on ways to improve the reliability of the results, it appears that the main bottleneck of the approach is the definition of an information-rich input space. Finding the appropriate measurements that are both cheap and meaningful is a task that has not yet been automated. In this framework, feature selection is a necessary tool to explore possible candidates. In this paper a hybrid method is proposed that lay between filtering and wrapper-based methods, trying to strike the right balance between accuracy and speed for the particular case of Alternate Test.