Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

11-2026

Abstract

We present a replicable data-mining pipeline for illustrative, scenario-conditioned corporate distress analysis under feature decoupling. The pipeline links Compustat financial statements with Sustainalytics ESG Risk Rating records for 2,144 U.S. non-financial public firms, constructs a standardized Transition Risk Index (TRI), estimates a contemporaneous accounting-distress classifier, and applies transparent transition-cost sensitivities. Distress is defined as annual operating income insufficient to cover annual interest expense; interest coverage itself is excluded from the predictors. The resulting model is not a forward default forecast or a regulatory probability-of-default model. On a held-out cross-sectional test set, the logistic specification obtains AUC 0.909, PR-AUC 0.822, and Brier score 0.105, outperforming a modified Altman-style Z″ proxy by ΔAUC = 0.135 (95% CI [0.073, 0.196], p

Keywords

Credit risk, climate transition risk, ESG analytics, stress testing, logistic regression, Sustainalytics, applied data mining, financial distress classification

Discipline

Databases and Information Systems | Finance

Research Areas

Data Science and Engineering

Areas of Excellence

Digital transformation

Publication

Proceedings of the 26th IEEE International Conference on Data Mining (ICDM 2026), Shenyang, China, November 12-15

First Page

1

Last Page

7

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Download

Share

COinS