Heterogeneous Effects of Green Finance on Urban Decarbonization: Evidence from 285 Cities in China
Summary
This study uses econometric models and machine learning (SHAP analysis) to examine how green finance reduces carbon intensity across 285 Chinese cities, finding heterogeneous effects by city tier and financial instrument, with green bonds and investment being most impactful.
View Cached Full Text
Cached at: 06/08/26, 09:19 AM
# Heterogeneous Effects of Green Finance on Urban Decarbonization: Evidence from 285 Cities in China Source: [https://arxiv.org/abs/2606.06986](https://arxiv.org/abs/2606.06986) [View PDF](https://arxiv.org/pdf/2606.06986) > Abstract:While green finance has become a key instrument for low\-carbon city transitions, its actual decarbonization effects and transmission mechanisms remain unclear\. This study employs econometric models and machine learning\-based analysis to examine whether and how green finance reduces city\-level carbon intensity\. Results show that green finance significantly lowers carbon intensity, with green bonds and green investment having the strongest impacts and evident spatial spillovers\. The effects vary by development level, being most pronounced in Fourth\- and Fifth\-tier cities\. Mediation analysis reveals that green finance operates mainly through energy structure optimization, followed by industrial upgrading, foreign direct investment, and technological innovation\. SHAP analysis confirms substantial differences across financial instruments, with green bonds, funds, and credit contributing most to decarbonization\. Moreover, the marginal impact is stronger in cities with low technological capacity, high industrial dependency, and coal\-based energy mixes\. These findings provide theoretical support and policy guidance for building a multi\-level, regionally differentiated green finance system to promote inclusive low\-carbon transitions\. Keywords: Green Finance; Carbon Intensity; Decarbonization Effect; Machine Learning; City ## Submission history From: Xueyang Li \[[view email](https://arxiv.org/show-email/7bffef89/2606.06986)\] **\[v1\]**Fri, 5 Jun 2026 07:24:43 UTC \(606 KB\)
Similar Articles
AI for Social Good: An Investigation of the Causal Relationship Between Environmental Regulations and Their Effects on Air Pollution in London, UK
This paper develops a Bayesian deep learning framework to estimate the causal effect of air pollution regulations on PM2.5 concentrations in London from 2010 to 2020, finding an average reduction of 1.88 μg/m³ (12.35%).
Can urban economics help model and improve agentic AI systems?
This article explores how concepts from urban economics, such as traffic, zoning, and pollution, can model externalities in agentic AI systems. It introduces a Behavioral Externality Multiplier (BEM) and proposes a layered framework involving architecture, substrate, and governance to measure and mitigate costly consequences of cheap AI actions.
@CinnabarOcean: For those interested in China's economic operation, local governance, and the new energy vehicle industry chain, I recommend following @FengmingLuPE long-term.
Recommends following @FengmingLuPE for insights on China's economy and EV industry; his new article argues that strategic alliances between local governments and private firms, not top-down policy, drove China's EV dominance.
Forecasting Green Skill Demand in the Automotive Industry: Evidence from Online Job Postings
This paper presents an end-to-end pipeline for identifying and forecasting green skill demand using online job postings from Mexico's automotive industry. It benchmarks 15 time-series forecasting models, finding transformer-based models like FEDformer and Informer perform best, and introduces a two-dimensional framework to classify skills by growth dynamics.
An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Using Edge Intelligence
This paper presents an AI-driven framework for energy-efficient environmental monitoring in smart cities using edge intelligence and TinyML, which dynamically activates sensors based on spatiotemporal conditions to reduce energy consumption and extend sensor lifespan.