Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.19671743 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p class="MsoNormal"><strong><em><span>The economy's continued failure to achieve and maintain external sustainability could lead to structural weaknesses, persistent current account imbalances, and poorly thought-out exchange rate mechanisms, all exacerbated by ineffective macroeconomic strategies. These factors will lead to a heavy reliance on external debt and increased exposure to the volatility of global financial markets, ultimately leading to a lack of long-term economic growth. It is essential to recognize this challenge and apply new analytical tools alongside reform-oriented frameworks. In this study, the researchers present a new interdisciplinary approach that attempts to address these shortcomings by integrating deep learning methodologies with economic decision-making analysis. The approach demonstrates that sustainability is not a fixed endpoint, but rather a flexible and adaptive process, unlike traditional economic models. This approach incorporates behavioral variables (policy adaptability and institutional responsiveness) and traditional economic indicators (trade balances and debt ratios). This integration is achieved through a hybrid model architecture that combines the Analytical Hierarchy Process (AHP) with Deep Learning Models (DLM). Three important discoveries were made using this model. First, the dynamic weighting mechanism of the AHP-DLM model allows the identification and quantification of the interaction between economic and behavioral variables that influence sustainability trajectories, thus capturing nonlinear relationships often neglected in conventional models. Second, the path-correcting capability of policymakers provides them with the tools necessary not only to assess the current state of sustainability but also to simulate corrective interventions, thus facilitating proactive policymaking. Finally, the model's inherent contextual adaptability accommodates different economic contexts, thus addressing widespread criticisms of generic approaches in the sustainability literature. This research represents the first application of deep learning to dissect the relationship between structural economic inefficiencies and decision-making processes in the field of sustainability governance. By linking computational capabilities to hierarchical priorities, this study calls for a paradigm shift from reactive responses to proactive economic strategy formulation, providing a scalable framework for diagnosing and guiding economies toward an externally resilient and sustainable future.</span></em></strong></p>