Leaf Values as Coordinates: Exact Contrastive Explanation for Gradient-Boosted Ensembles

The paper proposes treating leaf values of a gradient‑boosted ensemble as coordinates in ℝ^M, turning the model into a linear function over these coordinates. This perspective allows exact contrastive explanations: the difference between two instances is a vector that is zero wherever they share a leaf, so the gap is attributed to a few coordinates linked to specific tree splits. The authors build a recourse method based on this representation, achieving near‑perfect reconstruction of the model’s decision and demonstrating competitive performance on tabular datasets, especially when recommendations are limited to actionable changes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.