Open your black box classifier
- Paulo Lisboa
Abstract
The transparency of machine learning models is central to good practice
when they are applied in high stakes applications. Recent developments
make this feasible for tabular data, which is prevalent in risk
modelling and computer-based decision support across multiple domains
including healthcare. Important motivating factors for interpretability
are outlined and practical approaches are summarised, signposting the
main methods available, with pointers to the supporting literature. A
key finding is that any black box classifier making probabilistic
predictions of class membership from data in tabular form can be
represented with a globally interpretable model without loss of
performance.11 May 2023Submitted to Healthcare Technology Letters 13 May 2023Submission Checks Completed
13 May 2023Assigned to Editor
24 May 2023Reviewer(s) Assigned
03 Jul 2023Review(s) Completed, Editorial Evaluation Pending
03 Jul 2023Editorial Decision: Accept