Spatio-temporal neural structural causal models for bike flow prediction

TL;DR

This paper introduces a causality-based spatio-temporal neural model for bike flow prediction that effectively accounts for contextual influences and inter-regional causality, outperforming existing methods especially under external fluctuations.

Contribution

The paper presents a novel causal graph framework, applies the frontdoor criterion, and develops a counterfactual reasoning module for improved bike flow prediction.

Findings

Superior prediction accuracy on real-world datasets.

Enhanced robustness against external environmental fluctuations.

Effective elimination of confounding biases in feature extraction.

Abstract

As a representative of public transportation, the fundamental issue of managing bike-sharing systems is bike flow prediction. Recent methods overemphasize the spatio-temporal correlations in the data, ignoring the effects of contextual conditions on the transportation system and the inter-regional timevarying causality. In addition, due to the disturbance of incomplete observations in the data, random contextual conditions lead to spurious correlations between data and features, making the prediction of the model ineffective in special scenarios. To overcome this issue, we propose a Spatio-temporal Neural Structure Causal Model(STNSCM) from the perspective of causality. First, we build a causal graph to describe the traffic prediction, and further analyze the causal relationship between the input data, contextual conditions, spatiotemporal states, and prediction results. Second, we propose to apply the frontdoor criterion to eliminate confounding biases in the feature extraction process. Finally, we propose a counterfactual representation reasoning module to extrapolate the spatio-temporal state under the factual scenario to future counterfactual scenarios to improve the prediction performance. Experiments on real-world datasets demonstrate the superior performance of our model, especially its resistance to fluctuations caused by the external environment. The source code and data will be released.