Application of internet of things (IoT) and machine learning (ML) in intelligent logistics supply chain

Supply chain (SC) logistics efficiency is vital for competitiveness in today’s data-driven global economy. This study presents an intelligent, predictive logistics framework integrating the Internet of Things (IoT) and Machine Learning (ML) to enhance real-time decision-making. Conventional SC management approaches struggle to address the complexity and dynamism of modern logistics systems; hence, this research introduces the Logistics-based Hybrid Honey Bees Optimization–Deep Neural Network (LHHBO-DNN) model. The framework employs IoT-sensed data for continuous learning, enabling adaptive demand forecasting that directly supports procurement, inventory management, and transportation planning. Using the publicly available “Supply Chain Dataset of a Multi-Product Retailer” from Kaggle, the data were preprocessed and modeled through the LHHBO algorithm for hyperparameter optimization within a Deep Neural Network. Experimental results, implemented in Python, demonstrate that the proposed LHHBO-DNN model achieves higher forecasting accuracy and robustness compared with conventional predictive methods. The findings highlight the potential of IoT–ML integration to improve supply chain responsiveness, minimize downtime, and enhance overall logistics efficiency. The study demonstrates the strong potential of integrating Internet of Things (IoT) technologies with machine learning (ML) to enhance supply chain responsiveness, reduce operational downtime, and improve overall logistics efficiency. Supply chain management (SCM) is emphasized as a critical function for coordinating interdependent organizations to ensure the smooth flow of goods, information, and capital. The paper illustrates the practical implementation of real-time IoT data streams combined with ML-based predictive analytics to enable intelligent and data-driven logistics management.