Bardos, A., Mylonas, N., Mollas, I., Tsoumakas, G. (2023) Local interpretability of random forests for multi-target regression, Proceedings of the AIMLAI Workshop of ECML PKDD 2023.
Multi-target regression is useful in a plethora of applications. Although random forest models perform well in these tasks, they are often difficult to interpret. Interpretability is crucial in machine learn- ing, especially when it can directly impact human well-being. Although model-agnostic techniques exist for multi-target regression, specific tech- niques tailored to random forest models are not available. To address this issue, we propose a technique that provides rule-based interpretations for instances made by a random forest model for multi-target regres- sion, inspired by a recent model-specific technique for random forest in- terpretability. The proposed technique was evaluated through extensive experiments and shown to offer competitive interpretations compared to state-of-the-art techniques.