Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark

TL;DR

This paper introduces a unified framework and benchmark to evaluate how well different contextual features and modeling techniques generalize across various citywide crowd mobility prediction tasks, revealing key insights and guiding future research.

Contribution

It presents a comprehensive analytic framework and large-scale benchmark for assessing context generalizability in crowd mobility prediction, with experimental insights and recommendations.

Findings

More contextual features do not always improve predictions.

Holiday and temporal position provide highly generalizable information.

Gated units enhance the generalizability of context modeling techniques.

Abstract

Contextual features are important data sources for building citywide crowd mobility prediction models. However, the difficulty of applying context lies in the unknown generalizability of contextual features (e.g., weather, holiday, and points of interests) and context modeling techniques across different scenarios. In this paper, we present a unified analytic framework and a large-scale benchmark for evaluating context generalizability. The benchmark includes crowd mobility data, contextual data, and advanced prediction models. We conduct comprehensive experiments in several crowd mobility prediction tasks such as bike flow, metro passenger flow, and electric vehicle charging demand. Our results reveal several important observations: (1) Using more contextual features may not always result in better prediction with existing context modeling techniques; in particular, the combination of holiday and temporal position can provide more generalizable beneficial information than other contextual feature combinations. (2) In context modeling techniques, using a gated unit to incorporate raw contextual features into the deep prediction model has good generalizability. Besides, we offer several suggestions about incorporating contextual factors for building crowd mobility prediction applications. From our findings, we call for future research efforts devoted to developing new context modeling solutions.