Multistep Ahead Forecasting of WTI Crude Oil Prices Using Time Series and Machine Learning Models
Bibliographic record
Abstract
Crude oil is a critical energy source and a raw material for various products, including fuels (gasoline, diesel, and jet fuel), lubricants, petrochemicals, and asphalt. It undergoes refining processes to separate and convert it into usable products. Multiple factors, including economic indicators, geopolitical events, supply and demand dynamics, and technological advancements influence crude oil prices. Its global market has prices often benchmarked to grades like Brent Crude and West Texas Intermediate (WTI). In this article, the daily WTI crude oil prices are multi-step ahead forecasted using four different methods which are autoregressive integrated moving average (ARIMA), random forest (RF), k-nearest neighbors (kNN), and autoregressive neural networks (ARNN). The data set consists of daily WTI crude oil prices from February 13, 2014, to February 13, 2024, divided into 80% training set and 20% validation set. The performance of the methods is evaluated by one-step and seven-step ahead forecasting using root mean square error (RMSE) and mean absolute percentage error (MAPE) as the accuracy measures. The results show that ARIMA outperforms the methods for one and seven-step ahead forecasting, followed by ARNN, kNN, and RF. The study provides useful insights for investors and policymakers in the oil market.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 source (direct Gemma or distilled Codex), 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".