Climate Risk and Sustainable Entrepreneurial Adaptation: Evidence From Cross‐Country Microdata
気候リスクと持続可能な起業家適応:クロスカントリー・ミクロデータからのエビデンス (AI 翻訳)
Nguyễn Thị Hoa Hồng, Hoang Minh Hieu, Nguyen Tien Dat
🤖 gxceed AI 要約
日本語
気候リスクが起業家の持続可能な適応行動(SEA)に与える影響を、GEMデータと国別気候リスク指標を用いてMLモデルで分析。物理的気候リスクと適応準備性が主要な予測因子で、イノベーションとミッション志向が高リスク下の悪影響を緩和することを示す。
English
This study uses machine learning (Logistic Regression, Random Forest, XGBoost, Deep ANN with SHAP) on Global Entrepreneurship Monitor microdata to predict Sustainable Entrepreneurial Adaptation (SEA) under climate risk. Physical climate risk and national adaptive readiness are dominant predictors; innovation and mission-driven motivation mitigate harm from severe risk, positioning entrepreneurs as key climate agents.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本では、気候リスクと起業支援を結ぶ政策設計に示唆を与える。日本特有のデータや制度への直接適用は限定的だが、企業家の気候適応行動を理解する上で有用な分析枠組みを提供する。
In the global GX context
Adds micro-evidence on how climate risk shapes sustainable entrepreneurship across countries, using interpretable ML. Relevant to global policy frameworks linking climate adaptation, innovation ecosystems, and SDG-oriented entrepreneurship.
👥 読者別の含意
🔬研究者:Demonstrates an interpretable ML pipeline (SHAP, PDP) for cross-country microdata on climate adaptation.
🏛政策担当者:Provides evidence for designing policies that support climate-adaptive entrepreneurship, including innovation and mission-driven incentives.
📄 Abstract(原文)
ABSTRACT Climate change is reshaping entrepreneurial ecosystems, yet evidence on individual‐level sustainability‐oriented adaptation remains scarce. This study examines how multidimensional climate risk predicts Sustainable Entrepreneurial Adaptation (SEA) using cross‐country microdata. By focusing on individual decision‐makers, we address a critical gap in the micro‐foundations of climate resilience. We integrate Global Entrepreneurship Monitor data with country‐level indicators (CPRI, ND‐GAIN, and Global Climate Risk Index). Employing probabilistic classifiers, including Logistic Regression, Random Forest, XGBoost, and Deep ANN interpreted through SHAP and Partial Dependence Plots, we identify dominant predictors and nonlinear interaction patterns. Results show that physical climate risk and national adaptive readiness are primary predictors of SEA, alongside innovation and prosocial motivation. Notably, innovation and mission‐driven motivation mitigate the adverse effects of severe climate risk. The findings identify entrepreneurs as key agents of climate action, underscoring the importance of policy frameworks integrating climate risk, institutional context, and innovation support to achieve sustainable development goals.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1002/sd.71433first seen 2026-07-31 05:15:08
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録(無料・3キーワードまで)。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。