Causal Discovery and Inference towards Urban Elements and Associated Factors

TL;DR

The paper tackles the challenge that correlations among urban factors can be confounded and misleading for understanding city dynamics. It introduces a deep reinforcement learning framework to discover a causal DAG across 16 urban factors spanning Citizens, Locations, and Mobility, and uses propensity-score matching to estimate deconfounded causal effects on edges via $ATE$ concepts; significant edges are then used to prune inputs and improve urban mobility predictions. The resulting three-tier hierarchical graph positions citizens at the top, influencing locations and mobility, and reveals causal directions that can diverge from simple correlations. Empirically, propensity-score balancing validates the causal effects, and causal-significance-based input selection yields robust improvements in mobility prediction under limited training data, suggesting practical utility for urban planning and resource management.

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.

Figures (10)

• Figure 1: Statistics of the urban dataset.
• Figure 2: The framework of our method.
• Figure 3: The framework of causal discovery method via deep reinforcement learning.
• Figure 4: The framework of estimating causal effects.
• Figure 5: Four sub-graphs of our discovered causal graphs.