Saved in:
Bibliographic Details
Main Authors: Kim, Dongseok, Choi, Hyoungsun, Rasool, Mohamed Jismy Aashik, Oh, Gisung
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.07578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917455862956032
author Kim, Dongseok
Choi, Hyoungsun
Rasool, Mohamed Jismy Aashik
Oh, Gisung
author_facet Kim, Dongseok
Choi, Hyoungsun
Rasool, Mohamed Jismy Aashik
Oh, Gisung
contents Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but do not indicate whether their effects admit clear directional summaries, how uncertain those summaries are, or how faithfully they represent the fitted response. This paper proposes the $ϕ$-table, a SHAP-based statistical explanation table for tabular black-box regression models. The procedure selects features by SHAP importance and fits a standardized linear surrogate to the fitted model response $f(X)$, reporting SHAP importance together with model-response coefficients, uncertainty summaries, surrogate fidelity, and bootstrap coefficient stability. The resulting coefficients are interpreted as projections of the fitted model response onto the SHAP-selected feature set. Across synthetic, semi-synthetic, and real-data experiments, the $ϕ$-table extends ranking-only SHAP into a statistical global explanation by exposing direction, uncertainty, fidelity, and stability as distinct components of fitted model behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07578
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle $ϕ$-Table: A Statistical Explanation for Global SHAP
Kim, Dongseok
Choi, Hyoungsun
Rasool, Mohamed Jismy Aashik
Oh, Gisung
Machine Learning
Methodology
Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but do not indicate whether their effects admit clear directional summaries, how uncertain those summaries are, or how faithfully they represent the fitted response. This paper proposes the $ϕ$-table, a SHAP-based statistical explanation table for tabular black-box regression models. The procedure selects features by SHAP importance and fits a standardized linear surrogate to the fitted model response $f(X)$, reporting SHAP importance together with model-response coefficients, uncertainty summaries, surrogate fidelity, and bootstrap coefficient stability. The resulting coefficients are interpreted as projections of the fitted model response onto the SHAP-selected feature set. Across synthetic, semi-synthetic, and real-data experiments, the $ϕ$-table extends ranking-only SHAP into a statistical global explanation by exposing direction, uncertainty, fidelity, and stability as distinct components of fitted model behavior.
title $ϕ$-Table: A Statistical Explanation for Global SHAP
topic Machine Learning
Methodology
url https://arxiv.org/abs/2512.07578