Research on Supply Chain Network Optimisation Based on the CNNs-BiLSTM Model

Supply chain management is becoming more and more crucial to corporate operations as the global economy grows quickly and market rivalry heats up. Traditional supply chain optimisation methods often have difficulty meeting the needs of complex market environments, especially when dealing with large amounts of nonlinear time-series data. To address this problem, this study proposes a deep learning model based on a combination of convolutional neural networks (CNNs) and bidirectional long short-term memory networks (BiLSTMs), namely the CNNs-BiLSTM model, to improve the optimisation capability of supply chain networks. Experiments were conducted using real data from a large manufacturing company to evaluate the performance of the model and compare it with traditional single models. The experimental results show that the CNNs-BiLSTM model outperforms other models in terms of multiple key indicators such as accuracy, precision, recall and F1-score, demonstrating its effectiveness and adaptability in supply chain demand forecasting. The research results provide new perspectives and solutions for supply chain management, and have important theoretical and practical significance.