Supply chain delivery delays investigate the remarkable complications to the international market, interrupting activities, and rising expenses. Estimating supply chain delivery delays can enable companies to execute preemptive steps, reduce costs, and enhance customer satisfaction. This study aims to predict supply chain delivery delay risks using microeconomic indicators by applying a deep learning approach. The model evaluated structures and connections that conventional methods frequently ignore by utilizing datasets, GDP, price hikes, trade indicators, and industrial output data with an accuracy of 99.61%. The study outcomes executed on practical world datasets display the robustness and flexibility of our method of study and distributing achievable comprehensions for supply chain investors. This research aids in improving forecasting methods in supply chain management, with consequences for determining threat management roadmaps.