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

arXiv: https://arxiv.org/abs/2009.09379 · HTML: https://mlsanity.com/paper/2009.09379/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Spatiotemporal-Augmented Graph Neural Networks for Human Mobility Simulation](https://mlsanity.com/paper/2306.09381/) (2023)
- [A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management](https://mlsanity.com/paper/2306.02806/) (2023)
- [Multi-Factor Spatio-Temporal Prediction based on Graph Decomposition Learning](https://mlsanity.com/paper/2310.10374/) (2023)
- [Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect](https://mlsanity.com/paper/2207.10941/) (2022)
- [Knowledge-inspired Subdomain Adaptation for Cross-Domain Knowledge Transfer](https://mlsanity.com/paper/2308.09724/) (2023)
- [A Unified Model for Spatio-Temporal Prediction Queries with Arbitrary Modifiable Areal Units](https://mlsanity.com/paper/2403.07022/) (2024)
- [Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark](https://mlsanity.com/paper/2106.16046/) (2021)
- [Robust Traffic Forecasting against Spatial Shift over Years](https://mlsanity.com/paper/2410.00373/) (2024)
- [STContext: A Multifaceted Dataset for Developing Context-aware Spatio-temporal Crowd Mobility Prediction Models](https://mlsanity.com/paper/2501.03583/) (2025)
- [Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution](https://mlsanity.com/paper/2506.07179/) (2025)
- [UCTB: An Urban Computing Tool Box for Building Spatiotemporal Prediction Services](https://mlsanity.com/paper/2306.04144/) (2023)
- [Efficient User Sequence Learning for Online Services via Compressed Graph Neural Networks](https://mlsanity.com/paper/2406.02979/) (2024)

## Abstract (arXiv)

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.