Comparative Evaluation of Explanation Reliability in Shipment-Level Supply Chain Risk Classification: A Leakage-Checked Benchmark of XGBoost and a Hybrid XGBoost–Neural Framework with SHAP and LIME
Information · 19.11.2026 · 17 (11) · 1181
DOI: 10.3390/info17111181 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 19.11.2026. Verfasst von Sakib Salam Jamee und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Machine learning can forecast supply chain disruptions, but black-box models limit transparency, and the reliability of post-hoc explanations is rarely evaluated. We provide a leakage-checked, reproducible comparative benchmark for shipment-level risk classification on a public synthetic dataset of 5000 shipments, comparing XGBoost alone with a hybrid XGBoost–neural model (XAI-SC-RiskNet), both explained with SHAP and LIME. The hybrid (71.60% accuracy, ROC-AUC 0.819) is statistically indistinguishable from XGBoost (72.60%, 0.819; McNemar’s test p=0.123), as repeated cross-validation and a chronological hold-out confirm. On 500 test shipments, the Local Explanation Consensus Index (LECI; top-6 overlap of local SHAP and LIME features) and LIME stability are lower for the hybrid (0.57 versus 0.68; 0.80 versus 0.88), so the hypothesis that hybridization stabilizes explanations is not supported. LECI was modestly associated with misclassification (AUC 0.61) but added no significant information to predictive uncertainty (AUC 0.77); it is therefore a descriptive measure of explanation agreement, which does not establish explanation correctness or better decisions, and not a validated quality-control mechanism. These findings are specific to one synthetic benchmark with a concentrated weather signal and do not show that hybrid architectures are generally inferior.
Zitieren
APA
Jamee, S. S., Barua, A., Islam, M. S., Riipa, M. B., Rahman, S., Khan, M. I., & Ahmed, K. R. (2026). Comparative Evaluation of Explanation Reliability in Shipment-Level Supply Chain Risk Classification: A Leakage-Checked Benchmark of XGBoost and a Hybrid XGBoost–Neural Framework with SHAP and LIME. Information, 17(11), 1181. https://doi.org/10.3390/info17111181
Vancouver
Jamee SS, Barua A, Islam MS, Riipa MB, Rahman S, Khan MI, et al. Comparative Evaluation of Explanation Reliability in Shipment-Level Supply Chain Risk Classification: A Leakage-Checked Benchmark of XGBoost and a Hybrid XGBoost–Neural Framework with SHAP and LIME. Information. 2026;17(11):1181. doi:10.3390/info17111181
BibTeX
@article{Jamee2026,
author = {Jamee, Sakib Salam and Barua, Ayan and Islam, Md Shahidul and Riipa, Muslima Begom and Rahman, Shamimur and Khan, Mainul Islam and Ahmed, Khandakar Rabbi},
title = {Comparative Evaluation of Explanation Reliability in Shipment-Level Supply Chain Risk Classification: A Leakage-Checked Benchmark of XGBoost and a Hybrid XGBoost–Neural Framework with SHAP and LIME},
journal = {Information},
year = {2026},
volume = {17},
number = {11},
pages = {1181},
doi = {10.3390/info17111181}
}
EUVIMED