Applying Machine Learning to Strategic Market Prioritization in the Dairy Export Sector | ||
| Journal of Agricultural Science and Technology | ||
| Articles in Press, Accepted Manuscript, Available Online from 16 September 2025 PDF (1.89 M) | ||
| Authors | ||
| Morteza Majidian1; Esmaeil Pishbahar* 2 | ||
| 1Master's Student, Department of Agricultural Economics, University of Tehran, Karaj, Iran. | ||
| 2Full Professor, Department of Agricultural Economics, University of Tehran, Karaj, Iran. | ||
| Abstract | ||
| This study presents an innovative framework for optimizing Iran’s dairy exports by integrating machine learning and multi-criteria decision-making techniques. Utilizing a comprehensive 20-year dataset spanning 2003 to 2022, sourced from credible international databases, four machine learning models, Bagging Regression, CatBoost Regression, Gradient Boosted Regression, and Extreme Gradient Boosting, were employed to forecast dairy export values. The CatBoost Regression model demonstrated superior predictive accuracy, achieving a coefficient of determination of 0.93. To enhance interpretability, SHAP analysis was applied, revealing population, economic size, and trade potential as the most influential factors driving export performance. Concurrently, the TOPSIS method was used to prioritize potential export markets based on economic and trade-related criteria, identifying Turkey, Iraq, and Pakistan as the top destinations due to their proximity, market demand, and trade compatibility. This dual approach combines predictive analytics with strategic market ranking, offering actionable insights for policymakers and exporters aiming to bolster Iran’s non-oil economy. The findings highlight the critical role of regional markets and trade infrastructure in enhancing dairy export competitiveness. By leveraging advanced analytics, this research supports sustainable agricultural development and economic diversification in Iran, addressing the vulnerability of its oil-dependent economy. The methodology and results provide a robust foundation for future export strategies, emphasizing the synergy between data-driven forecasting and systematic decision-making in agricultural trade optimization. | ||
| Keywords | ||
| Dairy Exports; Machine learning; multi-criteria decision-making; Predictive Analytics; Trade Optimization | ||
| References | ||
|
| ||
|
Statistics Article View: 265 PDF Download: 168 |
||
| Number of Journals | 45 |
| Number of Issues | 2,171 |
| Number of Articles | 24,674 |
| Article View | 24,436,196 |
| PDF Download | 17,551,337 |