LionForests: Local Interpretation of Random Forests
This addresses the need for interpretability in machine learning systems, particularly in high-stakes domains like medical and finance, where trust is crucial, though it appears incremental as it builds on existing techniques for tree ensembles.
The paper tackles the problem of interpreting black-box random forest predictions by introducing LionForests, a method that uses unsupervised learning and an enhanced similarity metric to generate simple, comprehensive rules for local interpretations.
Towards a future where machine learning systems will integrate into every aspect of people's lives, researching methods to interpret such systems is necessary, instead of focusing exclusively on enhancing their performance. Enriching the trust between these systems and people will accelerate this integration process. Many medical and retail banking/finance applications use state-of-the-art machine learning techniques to predict certain aspects of new instances. Tree ensembles, like random forests, are widely acceptable solutions on these tasks, while at the same time they are avoided due to their black-box uninterpretable nature, creating an unreasonable paradox. In this paper, we provide a methodology for shedding light on the predictions of the misjudged family of tree ensemble algorithms. Using classic unsupervised learning techniques and an enhanced similarity metric, to wander among transparent trees inside a forest following breadcrumbs, the interpretable essence of tree ensembles arises. An interpretation provided by these systems using our approach, which we call "LionForests", can be a simple, comprehensive rule.