Predictive Modeling of Peanut Oil Prices Utilizing a Gaussian Process Regression-Based Machine Learning Framework
Bibliographic record
Abstract
Accurate anticipation of fluctuations in commodity valuations is critical for diverse stakeholders, encompassing policymakers, investors, and supply chain entities, to ensure informed decision-making within volatile markets. As a staple edible oil, peanut oil exhibits pronounced price volatility, necessitating robust predictive frameworks to mitigate economic risks. This study leverages a decade-long weekly wholesale price index data set (January 1, 2010–January 10, 2020) to model price dynamics within the Chinese agricultural sector. A Gaussian process regression (GPR) methodology is implemented, integrating Bayesian optimization for hyperparameter tuning and [Formula: see text]-fold cross-validation to systematically evaluate diverse kernel functions and basis configurations. Empirical validation reveals the model’s predictive efficacy, achieving a relative root mean square error (RRMSE) of 0.6823% during the out-of-sample evaluation phase (January 5, 2018–January 10, 2020), underscoring its reliability in capturing nonlinear price trends. The proposed machine learning framework not only serves as an autonomous tool for generating technical price projections but also can complement ensemble forecasting systems by synthesizing insights with econometric or fundamental models. Forecast results here could enhance the granularity of commodity market analyses, offering policymakers and analysts multidimensional perspectives for strategic planning and policy research.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".