eXplainable Random Forest

Advanced machine learning models have become widely adopted in various domains due to theirexceptional performance. However, their complexity often renders them difficult to interpret, whichcan be a significant limitation in high-stakes decision-making scenarios where explainability is crucial.In this study we propose eXplainable Random Forest (XRF), an extension of the Random Forest modelthat takes into consideration, crucially, during training, explainability constraints stemming from theusers’ view of the problem and its feature space. While numerous methods have been suggested forexplaining machine learning models, these methods often are suitable for use only after the modelhas been trained. Furthermore, the explanations provided by these methods may include features thatare not human-understandable, which in turn may hinder the user’s comprehension of the model’sreasoning. Our proposed method addresses these two limitations. We apply our proposed method to sixpublic benchmark datasets in a systematic way and demonstrate that XRF models manage to balance thetrade-off between the models’ performance and the users’ explainability constraints.