A Hybrid Machine Learning Techniques and Statistical Model for Forecasting the Export Value of Durian
Bibliographic record
Abstract
Abstract Over the past 20 years, the value of Thailand’s fresh durian exports has steadily increased, establishing durian as a significant agricultural export product. This study aims to identify the key factors influencing Thailand’s durian export value and develop accurate forecasting models using a combination of statistical and machine learning methods. Quarterly data from 2002 to 2022, spanning 84 quarters, was analyzed using four statistical approaches—Winter’s Exponential Smoothing, Seasonal Autoregressive Integrated Moving Average (SARIMA), Multiple Linear Regression, and Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX)—and two machine learning techniques—Support Vector Regression (SVR) and Multilayer Perceptron Neural Networks (MLP). A novel combined forecasting method, hybrid models, integrating statistical and machine learning models, was also developed to enhance predictive accuracy. The results revealed that the volume of Thailand’s durian exports and China’s gross domestic product (GDP) are significant factors positively correlated with the export value. In terms of forecasting accuracy, machine learning methods demonstrated superior performance compared to traditional statistical models. Notably, the combined SARIMAX-MLP model delivered the highest accuracy, outperforming both individual approaches. This study offers an innovative contribution by integrating statistical and machine learning techniques to improve forecasting precision for Thailand’s durian export value. These findings are valuable for policymakers, businesses, and researchers involved in agricultural export planning and management. The study also provides a foundation for future research, with potential applications of these methods to other agricultural products and sectors.
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 | 0.016 | 0.034 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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".