Integrating Big Data Analytics into Urban and Rural Grassroots Governance: A Framework for Decision-Making and Policy Optimization

Grassroots governance in urban and rural areas encounters multifaceted challenges in achieving efficiency, equity, and sustainability, particularly in the era of big data. This study proposes a big data-driven optimization model that integrates graph neural networks (GNNs) and multi-criteria decision-making analysis (MCDA) to address these challenges. By leveraging large-scale governance data, the model dynamically optimizes resource allocation, reduces service disparities, and balances competing objectives. Experimental results demonstrate that the framework makes resource matching 15.8% more accurate, pushes public service equity metrics up by 20.3%, and achieves a 10.2% improvement in ecological sustainability. The dynamic adaptation module significantly reduces strategy updating cycles by 30.0%, with emergency scenario re-planning response times controlled within 4.8 minutes. Therefore, the transformative potential of big data and advanced computational techniques in grassroots governance provides a scalable framework for fostering coordinated urban-rural development and advancing governance practices in the digital age.