Tracing Footsteps of Similar Cities: Modeling Urban Economic Vitality with Dynamic Inter-City Graph Embeddings

2025-11-27

AI Summary

Traditional static urban aggregation methods struggle to capture dynamic developmental trajectory similarities across cities. To address this, we propose ECO-GROW—a framework that constructs a dynamic multi-graph network of Chinese cities to model the long-term evolution of economic vitality. Methodologically, ECO-GROW innovatively integrates a dynamic Top-K graph convolutional network with an adaptive graph scoring mechanism and incorporates Barabási-proximity-based link prediction to model time-varying cross-regional influences. It jointly encodes industry interdependence, POI similarity, population migration flows, and temporal evolution patterns for city-level dynamic representation learning. Empirically, ECO-GROW achieves significant improvements over baseline models in entrepreneurial activity and employment trend forecasting—averaging a 12.7% gain in predictive accuracy. The implementation is publicly available. This work provides an interpretable, scalable, data-driven foundation for urban planning and evidence-based policymaking.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Game Theory and Economic Paradigms: Coordination and Collaboration

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Urban economic vitality is a crucial indicator of a city's long-term growth potential, comprising key metrics such as the annual number of new companies and the population employed. However, modeling urban economic vitality remains challenging. This study develops ECO-GROW, a multi-graph framework modeling China's inter-city networks (2005-2021) to generate urban embeddings that model urban economic vitality. Traditional approaches relying on static city-level aggregates fail to capture a fundamental dynamic: the developmental trajectory of one city today may mirror that of its structurally similar counterparts tomorrow. ECO-GROW overcomes this limitation by integrating industrial linkages, POI similarities, migration similarities and temporal network evolution over 15 years. The framework combines a Dynamic Top-K GCN to adaptively select influential inter-city connections and an adaptive Graph Scorer mechanism to dynamically weight cross-regional impacts. Additionally, the model incorporates a link prediction task based on Barabasi Proximity, optimizing the graph representation. Experimental results demonstrate ECO-GROW's superior accuracy in predicting entrepreneurial activities and employment trends compared to conventional models. By open-sourcing our code, we enable government agencies and public sector organizations to leverage big data analytics for evidence-based urban planning, economic policy formulation, and resource allocation decisions that benefit society at large.

Problem

• Modeling urban economic vitality using dynamic inter-city graph embeddings
• Overcoming static city-level aggregate limitations with multi-graph framework
• Predicting entrepreneurial activities and employment trends for urban planning

Innovation

• Dynamic multi-graph framework modeling inter-city networks
• Adaptive GCN and Graph Scorer for cross-regional impact weighting
• Link prediction optimization using Barabasi Proximity for representation