Development and Evaluation of Predictive Machine Learning Models for Crude Oil Supply Chain Logistics in the USA
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".