BellatrExplorer

Description:

BellatrExplorer is a dashboard application designed to interactively explore random forest predictions on the individual instance level. The application is inspired by the local interpretability toolbox Bellatrex, that exploits the internal random forest structure to extract 1-3 prototype rules that act as a surrogate model for an instance of interest. 

BellatrExplorer is aimed at expert users trying to better understand the behavior of their random forest in a specific application, and could allow to uncover potential biases or artifacts arising in model training. Currently, the tool supports random forests for binary classification, regression, and survival analysis tasks. It features (1) intuitive exploration of univariate predictive counterfactuals, (2) analysis of decision tree rules to the individual split level, and (3) a visualisation of the rules extracted by Bellatrex that allow to assess the local interpretation at a glance.

More Information:

• Originates from the AI-Driven Data Science research challenge (FAIR 2019–2023).

• Responsible Research Lead: Celine Vens

• Authors: Robbe D’hondt, Celine vens

• Programming Language: Python

• Link to the website

• Link to a tutorial video

• Link to the repository

• Categories: Supervised learning

Publications:

• Robbe D’hondt and Celine Vens. 2025. BellatrExplorer: An Interactive Random Forest Local Explainability Dashboard. In Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track and Demo Track: European Conference, ECML PKDD 2025, Porto, Portugal, September 15–19, 2025, Proceedings, Part X. Springer-Verlag, Berlin, Heidelberg, 465–469. https://doi.org/10.1007/978-3-032-06129-4_32