The delivery time of goods in the supply chain is a critical enabler for achieving overall supply chain excellence and business success. However, the uncertainty of the delivery times of goods is a significant issue, making it critical for businesses to develop effective logistics and shipping strategies. Accurately forecasting delivery times is needed to maintain smooth logistics operations and, ultimately, reduce overall transportation, shortage, and inventory costs. Consequently, the purpose of this paper is to propose machine learning algorithms for predicting the delivery time and enhancing the responsiveness of the supply chain in the oil and gas industry.  The proposed models will help in building a resilient supply chain capable of adapting to unforeseen events and disruptions. In this paper, the factors influencing the delivery time of the goods in the oil and gas supply chain are identified based on reviewing the literature and expert interviews. Different statistical analysis tests are conducted to ensure the quality of data. In addition, the correlation between the input factors and between input and output is investigated. The machine learning models are developed and validated using real data from an important field; the gas and oil industry.  The results indicated that the factors that influence the delivery time of the goods in oil and gas include annual order hits, priority, supplier region, product complexity, and transportation method. Moreover, the findings revealed the capability of the proposed models to predict the delivery time with an accuracy higher than 85%. This study provides managers with valuable tools for managing and optimizing their supply chain operations by highlighting the critical factors influencing delivery time and providing a reliable predictive model. In addition, the proposed models are expected to assess the organization in reducing supply chain transportation, inventory, and shortage costs.