Artificial Intelligence-Driven Decision Intelligence for Supply Chain Optimization: A Computational Framework for Resilient and Adaptive Operations
Computer and Decision Making An International Journal · 08.11.2026
DOI: 10.1922/comdem.v3i8s.19180 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making An International Journal, online erschienen am 08.11.2026. Verfasst von Dr. Santanu Roy und 3 weiteren Autor:innen.
Abstract (Originalsprache)
AI is now being implemented to enhance supply-chain predictions, risk forecasting and operational choices. This study proposes an AI-based decision intelligence framework for supply-chain optimization, focusing on resilient and adaptive aviation spare-parts operations. The quantitative computational design was used for 12,960 observations, each of a different spare part, aircraft type and operational location every month. Descriptive statistics, demand forecasting, stockout-risk prediction, feature-importance assessment and replenishment prioritization were all included in the analysis. Linear regression, decision tree, random forest and gradient boosting models were used to evaluate the demand forecasting and logistic regression and tree-based classifiers for the stockout prediction models. There were significant differences between stockout and non-stockout observations for demand but not for lead time, while the levels of opening and closing inventory were significantly lower during stockout observations compared to non-stockout observations. Linear regression was found to be the best model for the prediction of demand and gradient boosting was the best model for the prediction of stockout risk. The most significant variables to predict stockout were quantity of demand and opening inventory. Replenishment priority categories were developed using the predictive outputs such that the observed and predicted stockout risk was significantly higher for critical-priority observations than low-priority observations. The proposed framework illustrates how predictive analytics can be translated to operational decision intelligence for prioritizing inventory, preventing stockouts and planning for responsive replenishment. The results demonstrate the applicability of AI-driven computational tools to enhance resilient, adaptive and data-driven supply-chain management.
Zitieren
APA
Roy, D. S., P, G., Chandratreya, D. A., & Sahu, D. P. K. (2026). Artificial Intelligence-Driven Decision Intelligence for Supply Chain Optimization: A Computational Framework for Resilient and Adaptive Operations. Computer and Decision Making An International Journal. https://doi.org/10.1922/comdem.v3i8s.19180
Vancouver
Roy DS, P G, Chandratreya DA, Sahu DPK. Artificial Intelligence-Driven Decision Intelligence for Supply Chain Optimization: A Computational Framework for Resilient and Adaptive Operations. Computer and Decision Making An International Journal. 2026. doi:10.1922/comdem.v3i8s.19180
BibTeX
@article{Roy2026,
author = {Roy, Dr. Santanu and P, Gurulingu and Chandratreya, Dr. Abhijit and Sahu, Dr. Pratap Kumar},
title = {Artificial Intelligence-Driven Decision Intelligence for Supply Chain Optimization: A Computational Framework for Resilient and Adaptive Operations},
journal = {Computer and Decision Making An International Journal},
year = {2026},
doi = {10.1922/comdem.v3i8s.19180}
}
EUVIMED