Automatically tuning parameters in a layered model framework

One or more storage media storing instructions which, when executed by the one or more processors, cause:

• using one or more machine learning techniques to train a plurality of versions of a first model that includes a first version of the first model and a second version of the first model;
• storing a second model that includes a parameter and that accepts, as input, output from the first model;
• testing a plurality of parameter values of the parameter of the second model when processing a plurality of content requests using the first and second versions of the first model;
• selecting, for the parameter of the second model, a strict subset of the plurality of parameter values such that processing a first subset of the plurality of content requests using the first version of the first model results in a first value of a particular metric that matches a second value of the particular metric resulting from processing a second subset of the plurality of content requests using the second version of the first model.