TITLE:
Development and Evaluation of Predictive Machine Learning Models for Crude Oil Supply Chain Logistics in the USA
AUTHORS:
Maame Korkor Prah, Amina Yakubu, Lawrence Simon Attah, Adeyemi Oluwatoba
KEYWORDS:
Crude Oil, Import, Predictive Modelling
JOURNAL NAME:
Technology and Investment,
Vol.16 No.2,
April
23,
2025
ABSTRACT: Background and Theoretical Dilemma: The United States of America (USA) is the world’s largest consumer of crude oil in the world. Ensuring the sustainability of the role of crude oil in the USA makes the need for effective crude oil supply chain logistics to be important. Therefore, this study tested the predictive ability of two machine learning models such as random forest and support vector machine (SVM) in relation to a classical statistical method such as ARIMA (Autoregressive Integrated Moving Average) for predicting the volume of crude oil import into the USA from 2024 to 2034. Method: Crude oil import data used for the prediction were sourced from U.S. Energy Information Administration. The data contained importation data from 1973 to 2023. The performance of the predictive models was tested with mean absolute error (MAE) and Root Mean Square Error (RMSE). Key Findings and Conclusion: Among the three predictive approaches used, SVM had the least MAE (265.65) and RMSE (362.91). This was followed by random forest (MAE =479.37; RMSE = 620.75) while ARIMA had the poorest performance (MAE =1670.10; RMSE = 2195.91). This implies that SVM outperformed the other predictive model for determining the import of crude oil from 2023 to 2034. In addition, among the sources from which crude oil is being imported to USA, Iraq, Canada and Russia have the highest feature importance for the random forest model. This implies that machine learning approach not only help predicts the future supply need for crude oil, but also areas where logistic management should be targeted to.