Enhancing Supply Chain Efficiency through Advanced Machine Learning Models for Demand Forecasting and Queuing Analysis
Year: 2026
Type: article
Abstract: Supply chain optimisation (SCO) is essential for enhancing operational efficiency, reducing costs, and ensuring sustainability.With the increasing complexity of global supply chains, traditional approaches probably fail to address dynamic challenges, necessitating advanced tools like machine learning (ML).While ML has transformed demand forecasting and bottleneck analysis, limited research integrates these aspects for comprehensive supply chain management, creating a significant research gap.This study evaluates the performance of Random Forest, Gradient Boosting, and Linear Regression models for demand forecasting and queuing analysis.We have analysed the data which have been collected from the Kaggle dataset.Model optimisation is performed using hyperparameter tuning, with performance validated through metrics including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R² score.Results show that Random Forest achieved the lowest MAE (24.54) and RMSE (44.69) with the highest R² (0.86) for demand forecasting, followed by Gradient Boosting (MAE: 33.72, RMSE: 47.72, R²: 0.84.
DOI: 10.26573/2026.20.1.3
Authors: Anshu Rathi, Geetanjali Sharma
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W7224094050