OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction
For urban analytics practitioners, OpFlow offers a more robust method for OD flow prediction under distribution shift, though the improvement is incremental over existing deep learning approaches.
OpFlow improves robustness of OD flow prediction under distribution shift by learning transferable choice potentials that separate allocation mechanisms from origin-specific demand scales, outperforming baselines in synthetic and real-world experiments.
Origin-destination (OD) flow prediction is central to urban analytics, yet deep models trained on raw counts remain vulnerable to distribution shift. The core problem is that raw count supervision cannot distinguish transferable choice mechanisms from environment-specific shortcuts. Raw OD count mixes two objects: how much demand an origin produces and how that demand is allocated across destinations. We argue that the transferable object is the exposure-to-choice law that maps spatial conditions to relative destination preferences. We propose OpFlow, a mechanism-constrained framework that learns row-centered choice potentials and reconstructs flows by combining the induced allocation with a separately calibrated origin scale. Under distribution shift, spatial exposures and the induced allocations are allowed to vary; what transfers is the conditional map from exposure states to relative choice potentials. Theoretically, we characterize the identifiable row-centered potential and show that classical spatial interaction laws are restricted log-potential cases. Controlled synthetic shifts and a real-world experiment show OpFlow improves robustness under environment shifts.