| تعداد نشریات | 24 |
| تعداد شمارهها | 883 |
| تعداد مقالات | 7,877 |
| تعداد مشاهده مقاله | 14,800,084 |
| تعداد دریافت فایل اصل مقاله | 12,612,474 |
A Machine-Learning-Based Typology of Sustainable Development Pathways: Evidence from 19 Countries with a Special Focus on Iran | ||
| Iranian Journal of Economic Studies | ||
| مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 28 آذر 1404 | ||
| نوع مقاله: Research Paper | ||
| شناسه دیجیتال (DOI): 10.22099/ijes.2025.54083.2081 | ||
| نویسندگان | ||
| Forough Esmaeily Sadrabadi* 1؛ Samineh Ghasemifar2 | ||
| 1Department of Economics, Ardakan University, Ardakan, Iran. | ||
| 2Department of Economics and Accounting, University of Hormozgan, Bandarabbas, Iran. | ||
| چکیده | ||
| This study introduces a novel, fully unsupervised, data-driven typology of national sustainability pathways, aiming to identify distinct development trajectories across countries and to precisely locate Iran within a global context. The innovative methodological approach integrates K-means clustering optimized with the silhouette score, t-SNE visualization for high-dimensional data representation, and hierarchical clustering for robustness validation, providing a comprehensive and objective framework for cross-country comparison. Five core indicators—GDP per capita, CO₂ emissions per capita, renewable energy share, energy intensity, and the Human Development Index (HDI)—are used for 19 selected countries over 2021–2025. This multidimensional approach captures economic, environmental, and social dimensions of sustainability, allowing a detailed assessment of each country’s performance and trajectory. The results reveal four distinct pathways. Iran clusters with fossil fuel-dependent emerging economies, including China, India, Turkey, Malaysia, and Thailand. Among these peers, Iran exhibits the lowest renewable energy share (1.1%) and the highest energy intensity, positioning it on the most extreme fossil-fuel-locked trajectory worldwide. In contrast, leading countries such as Sweden achieve 62.9% renewable energy share, emphasizing a significant sustainability gap. These findings provide policymakers with a clear benchmarking tool and identify three urgent priorities for Iran: accelerating renewable energy investment, gradually reforming fossil-fuel subsidies, and modernizing energy infrastructure. Implementing targeted reforms along these lines could enable Iran to transition toward a more resilient, competitive, and low-carbon development path, aligning economic growth with environmental sustainability. | ||
| کلیدواژهها | ||
| Sustainable economic development؛ K-means clustering؛ machine learning؛ renewable energy؛ Iran’s position | ||
|
آمار تعداد مشاهده مقاله: 12 |
||