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{182050,
        author = {Anubhav Kumar Tiwary and Vishnupant Potdar and Shubhangi P. Tidake},
        title = {Enhancing Supply Chain Decision-Making and Strategic Planning using Machine Learning and Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {733-738},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182050},
        abstract = {Accurately estimating delivery times is a key challenge in optimizing last-mile logistics within the broader scope of supply chain management. This study presents a structured machine learning pipeline to predict delivery time using a real-world dataset comprising order details, geolocation, weather, traffic, and time-based factors. Various regression models were evaluated, including Linear Regression, Decision Tree with Bagging, Random Forest, ElasticNet, SVM, XGBoost, CatBoost, LightGBM (with Optuna tuning), and Neural Networks. Model performance was assessed via 5-fold cross-validation using metrics such as MSE, RMSE, MAE, and R² Score. CatBoost emerged as the top-performing model, achieving the highest R² score of 0.8666 and the lowest error rates. While ensemble models dominated in performance, Neural Networks were also explored for their ability to learn complex feature patterns. The results demonstrate the practical value of advanced machine learning in handling high-dimensional, noisy delivery data, offering actionable insights for improving delivery time predictions and enhancing overall supply chain efficiency.},
        keywords = {CatBoost, Cross-Validation, Delivery Time Prediction, Feature Engineering, Machine Learning, Neural Network, Regression Models, Supply Chain Management.},
        month = {July},
        }