Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework

TL;DR

This paper introduces an analytic framework and a meta-model for evaluating and enhancing the generalizability of spatio-temporal traffic prediction methods across diverse real-world scenarios.

Contribution

It proposes a qualitative analytic framework, a flexible meta-model, and a benchmark platform to compare and improve the generalizability of STTP approaches.

Findings

STMeta outperforms state-of-the-art methods in generalizability

The framework enables comparison of different STTP approaches

Benchmark results show improved prediction accuracy across datasets

Abstract

The Spatio-Temporal Traffic Prediction (STTP) problem is a classical problem with plenty of prior research efforts that benefit from traditional statistical learning and recent deep learning approaches. While STTP can refer to many real-world problems, most existing studies focus on quite specific applications, such as the prediction of taxi demand, ridesharing order, traffic speed, and so on. This hinders the STTP research as the approaches designed for different applications are hardly comparable, and thus how an application-driven approach can be generalized to other scenarios is unclear. To fill in this gap, this paper makes three efforts: (i) we propose an analytic framework, called STAnalytic, to qualitatively investigate STTP approaches regarding their design considerations on various spatial and temporal factors, aiming to make different application-driven approaches comparable; (ii) we design a spatio-temporal meta-model, called STMeta, which can flexibly integrate generalizable temporal and spatial knowledge identified by STAnalytic, (iii) we build an STTP benchmark platform including ten real-life datasets with five scenarios to quantitatively measure the generalizability of STTP approaches. In particular, we implement STMeta with different deep learning techniques, and STMeta demonstrates better generalizability than state-of-the-art approaches by achieving lower prediction error on average across all the datasets.