CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting

2026-06-03

AI Summary

This work addresses the cold-start challenge in predicting check-ins at new points of interest (POIs), which arises due to the absence of historical interaction data. To tackle this problem, the authors propose CausalPOI, a novel framework that introduces causal inference into POI recommendation for the first time. The method constructs a spatiotemporal functional interaction graph to capture semantic and spatial dependencies among POIs and employs structurally aligned treatment and control graphs to model factual and counterfactual scenarios under urban interventions. Extensive experiments on the real-world SafeGraph dataset demonstrate that CausalPOI significantly outperforms existing approaches in spatiotemporal prediction accuracy, semantic interaction modeling, and causal effect estimation, while also enhancing model interpretability and intervention analysis capabilities.

Abstract

As urban environments continue to evolve rapidly, accurately modeling the dynamic behaviour of Points of Interest is essential for supporting data-driven urban planning and commercial decision-making. While recent advancements in spatio-temporal graph learning have improved POI forecasting, most methods rely on proximity-based graphs and correlation-driven modeling, which overlook the functional dependencies between POIs and fail to capture the causal effects of urban interventions. In this paper, we introduce a novel research problem -- cold-start POI check-in forecasting, which aims to predict the future check-in pattern of a newly introduced POI, by modeling its temporal evolution and functional interactions with nearby POIs in a structured urban spatial context. To address these challenges, we propose CausalPOI, a spatio-temporal graph-based causal representation learning framework. CausalPOI leverages Spatio-Temporal Functional Interaction Graph to model semantic and spatial relationships between POIs, and constructs structurally aligned treatment and control graphs to simulate factual and counterfactual scenarios. Extensive experiments on real-world SafeGraph datasets demonstrate that CausalPOI significantly outperforms state-of-the-art baselines across the board, validating its effectiveness in spatio-temporal forecasting, semantic interaction modeling, and causal effect estimation, providing a more interpretable and actionable foundation for urban intervention analysis. Source code is available at Github.

Problem

• cold-start
• POI forecasting
• spatio-temporal
• causal modeling
• urban intervention

Innovation

• causal inference
• spatio-temporal graph
• cold-start POI forecasting
• functional interaction
• counterfactual modeling