Intelligent sorting optimization algorithm for e-commerce logistics cargo based on neural networks and deep learning

The rapid growth of e-commerce has intensified the demand for efficient logistics cargo management, necessitating advanced automation, IoT-enabled monitoring, and intelligent sorting systems. Although deep learning algorithms are widely used, issues of optimizing the cargo sorting process are still present because of the complexity of the spatial relations and the diversity of cargo types, which demonstrates the lack of adaptive and high-precision algorithms development in IoT-driven Logistics environment. This research presents an Intelligent Sorting Optimization Algorithm of e-commerce logistics cargo, which is based on neural networks and deep learning methods, and IoT-based data acquisition systems. Giant Armadillo Optimizer-based Graph Convolutional Neural Network (GAO -GCNN) to enhance the sorting process. E-commerce Logistics Cargo Dataset was obtained from a publicly available Kaggle source, comprising 3500 cargo instances, and used to simulate IoT-enabled e-commerce logistics conditions. Normalization and systematic outlier were included in the data pre-processing to handle sensor noise and IoT data variations, and principal component analysis (PCA) was used in extracting the features. The GAO process is used to optimize the hyperparameters, including learning rates, network weights, and the GCNN is used to combine the capabilities and form the inter-cargo relationships based on IoT-derived spatial and contextual data with the Convolutional Neural Network (CNN) operations to identify features accurately. The model was implemented in Python and evaluated using multiple performance metrics. Experimental results obtained using Python-based experimental settings demonstrate that the proposed model achieved an information recognition accuracy of 98.74%, sorting success rate of 98.5%, and an error rate of 0.5%. Comparative analysis with baseline methods such as DQN and MDFM shows consistent improvements across metrics, confirming GAO-GCNN effectiveness, enhancing cargo management, and supporting intelligent logistics systems and warehouse automation efficiency.