Machine Learning-based Analysis of Structural Contribution Patterns in Regional Financial Vulnerability

Q: What does this research mean for the field?

The structural drivers of financial vulnerability differ significantly by region, with metropolitan areas primarily influenced by employment and housing stability, and non-metropolitan areas driven by industrial and demographic factors, necessitating region-specific financial stability strategies. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

임해리; Jina Song; HyoYeon Kang; Jongtae Lee

doi:10.14801/jkiit.2026.24.8.11

August 31, 2026The Journal of Korean Institute of Information Technology

Machine Learning-based Analysis of Structural Contribution Patterns in Regional Financial Vulnerability

View at Publisher

Ask AI

Bookmark

Share

Key Points

Assess regional heterogeneity in financial vulnerability across 17 metropolitan governments and identify localized structural drivers using machine learning architectures.
Recalculated regional Financial Vulnerability Indices (FVI) across 17 South Korean metropolitan governments by integrating asset prices, credit accumulation, and financial resilience metrics.
Trained and evaluated predictive models using Random Forest, XGBoost, and LightGBM algorithms.
Analyzed structural contribution patterns and nonlinear macroeconomic sensitivities using SHAP values, K-means clustering, partial dependence plots, and shock scenario simulations.
XGBoost demonstrated the highest predictive performance among the evaluated machine learning models for forecasting regional financial vulnerability.
SHAP and K-means cluster analyses identified distinct regional risk profiles: capital areas are predominantly sensitive to housing stability and employment factors, whereas non-capital regions are primarily shaped by industrial and demographic structures.
Partial dependence plots and shock scenario analyses confirmed significant nonlinear responses and regional variation in sensitivity to macroeconomic shocks.

Implication

Predictive modeling study reveals divergent drivers of regional financial vulnerability across 17 Korean metropolitan governments, highlighting the need for localized financial stability policies.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

임해리 et al. (2026) studied this question.

synapsesocial.com/papers/6a9934cf636c6408cfa7c8c6 https://doi.org/10.14801/jkiit.2026.24.8.11

View at Publisher

Ask AI

Bookmark

Share

Machine Learning-based Analysis of Structural Contribution Patterns in Regional Financial Vulnerability

Key Points

Implication

Abstract

Discussion

Cite This Study

Machine Learning-based Analysis of Structural Contribution Patterns in Regional Financial Vulnerability

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading