Material Flow Prediction Task Based On TCN-GRU Deep Fusion Model

With the rapid development of e-commerce and smart logistics, the demand for accurate material flow prediction in logistics systems has become increasingly critical. Accurate forecasting not only enhances delivery efficiency and reduces operational costs but also supports key decisions such as warehouse scheduling, route optimization, and resource allocation. Effectively capturing the temporal dynamics of material flow under complex and variable traffic and weather conditions has emerged as a crucial research focus in the field of intelligent logistics. This study proposes a material flow prediction method based on a TCN-GRU deep fusion model, aiming to improve prediction accuracy and enhance the ability to capture both short-term and long-term dependencies in time series data. The model is evaluated using the Amazon Delivery Dataset, which comprises 43,632 delivery records across multiple cities, including detailed information on orders, delivery agents, weather, traffic conditions, and delivery performance metrics, providing a solid foundation for analyzing multivariate interactions affecting material flow. Focusing on the city of Chennai, India, this research particularly examines the impact of weather conditions on delivery performance and validates the effectiveness of the proposed model. The TCN (Temporal Convolutional Network) component efficiently extracts local temporal features, while the GRU (Gated Recurrent Unit) is adept at modeling long-term dependencies. Together, they enable the model to better capture complex temporal patterns. Experimental results demonstrate that the model achieves a Mean Absolute Error (MAE) of 1.860 in predicting material flow, outperforming traditional time series forecasting methods and showing clear advantages in both prediction accuracy and generalization capability.