Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{209114,
        author = {Sannidhi Kharvi and Lavanya V and Chithrakshi Naik},
        title = {Logistic Supply Chain Risk Prediction using AI/ML},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {757-762},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209114},
        abstract = {Contemporary multimodal logistics networks operate within complex stochastic environments characterized by sudden operational disruptions, localized transit friction, severe weather conditions, and terminal bottlenecks. Conventional supply chain management methodologies rely predominantly on reactive intervention strategies executed only after delivery delays have physically materialized, causing severe monetary penalties, inventory disruptions, and decreased customer satisfaction. This research designs and implements an intelligent, predictive, machinelearning-driven early-warning framework to forecast shipment delivery risks prior to departure. The system bridges historical shipment datasets with real-time dynamic context enrichment using the OpenWeather and OpenRouteService Application Programming Interfaces (APIs). A spectrum of classification algorithms including Logistic Regression, Decision Trees, Extreme Gradient Boosting (XGBoost), and Random Forest were empirically benchmarked. The ensemble Random Forest model attained superior performance, achieving a classification accuracy of 96.0%, a precision of 94.7%, and a disruption detection recall of 95.2%. The trained inference pipeline is operationalized within an interactive Streamlit web dashboard providing spatial route visualization via Folium, real-time risk gauge tracking, automated recommendation alerts, and downloadable decisionsupport dossiers.},
        keywords = {Artificial intelligence, decision trees, dynamic context enrichment, machine learning, predictive analytics, Random Forest, real-time systems, supply chain risk management.},
        month = {October},
        }