Machine learning analysis reveals heterogeneous land price declines under green belt restrictions in South Korea, suggesting a need for location-targeted urban planning interventions.
South Korea's green belt policy aims to restrict development to control urban sprawl, but its economic burden on landowners varies substantially across locations. Using the conditional average treatment effect (CATE) framework, target transformation and machine learning models, this study estimates the policy's heterogeneous effects on land prices. Results reveal pronounced price declines in highly urbanised areas and minimal impacts in provincial townships. While the policy's negative effects diminish with distance from Seoul's core, townships with strong development potential still face significant price reductions despite their peripheral locations. By applying CATE, policymakers can identify sensitive areas and design targeted interventions.
No takes yet. Share an insight, caveat, or question.
Changro Lee (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: