Practical Considerations for Specifying a Super Learner

Presented by Rachael Phillips. Super learner is a machine learning algorithm that uses cross-validation and a loss function to optimally combine a diversity of candidate algorithms into a “super learner” ensemble. The super learner is extremely flexible and entirely pre-specified, but how should it be constructed? In this webinar, we provide a flowchart for constructing a super learner in practice, discussing all arguments and recommending specific inputs. By the end of this talk, attendees will be equipped with a guide to refer to when specifying super learners for their statistical analysis plans.