Causal Probabilistic Spatio-temporal Fusion Transformers in Two-sided Ride-Hailing Markets

In this work, we address the complex problem of multi-objective time series forecasting with a focus on predicting interdependent targets such as supply and demand in ride-hailing services. Traditional machine learning techniques approach the targets independently, while deep learning strategies may use joint learning with shared representations, both neglecting inter-target causal relationships and potentially compromising the models’ generalization capabilities. Our novel CausalTrans model introduces a framework to define and leverage the temporal causal interplay between supply and demand, incorporating both temporal and spatial causality into the forecasting process. Additionally, we enhance computational efficiency by introducing an innovative fast attention mechanism that reduces the time complexity from quadratic to linear without sacrificing performance. Our comprehensive experiments show that CausalTrans significantly surpasses contemporary forecasting methods, achieving up to a 15 \(\% \) reduction in error, thus setting a new benchmark in the field.