Causal Discovery and Inference towards Urban Elements and Associated Factors

2025-03-09

AI Summary

Urban elements—citizens, locations, and mobility behaviors—exhibit complex interdependencies, yet empirical correlations are often confounded, obscuring true causal mechanisms. Method: We propose the first urban causal computing framework integrating reinforcement learning–based causal graph discovery with propensity score matching to systematically identify causal structures and confounders among these three elements. Causal graph search is optimized via reinforcement learning; confounding bias is controlled through propensity score matching; and causal effects are assessed via significance-driven evaluation. Contribution/Results: Experiments on open urban datasets reveal a hierarchical causal structure: “citizen → location → mobility behavior.” This learned structure improves mobility prediction accuracy by +12.7% and reduces confounding bias by 63.4% on average. Our framework establishes an interpretable, verifiable paradigm for causal modeling in urban computing.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

To uncover the city's fundamental functioning mechanisms, it is important to acquire a deep understanding of complicated relationships among citizens, location, and mobility behaviors. Previous research studies have applied direct correlation analysis to investigate such relationships. Nevertheless, due to the ubiquitous confounding effects, empirical correlation analysis may not accurately reflect underlying causal relationships among basic urban elements. In this paper, we propose a novel urban causal computing framework to comprehensively explore causalities and confounding effects among a variety of factors across different types of urban elements. In particular, we design a reinforcement learning algorithm to discover the potential causal graph, which depicts the causal relations between urban factors. The causal graph further serves as the guidance for estimating causal effects between pair-wise urban factors by propensity score matching. After removing the confounding effects from correlations, we leverage significance levels of causal effects in downstream urban mobility prediction tasks. Experimental studies on open-source urban datasets show that the discovered causal graph demonstrates a hierarchical structure, where citizens affect locations, and they both cause changes in urban mobility behaviors. Experimental results in urban mobility prediction tasks further show that the proposed method can effectively reduce confounding effects and enhance performance of urban computing tasks.

Problem

• Uncover causal relationships among urban elements
• Address confounding effects in urban correlation analysis
• Enhance urban mobility prediction using causal inference

Innovation

• Reinforcement learning for causal graph discovery
• Propensity score matching for causal effect estimation
• Hierarchical causal structure in urban elements