On the importance of stationarity, strong baselines and benchmarks in transport prediction problems
This work highlights the importance of stationarity and recurrent patterns in transportation data, providing benchmarks and best practices to guide future research in the field.
The paper tackles the overemphasis on spatial correlations in deep learning for spatio-temporal forecasting in transportation by showing that a naive baseline method based on average weekly patterns and linear regression achieves comparable or better results than state-of-the-art approaches on several datasets.
Over the last years, the transportation community has witnessed a tremendous amount of research contributions on new deep learning approaches for spatio-temporal forecasting. These contributions tend to emphasize the modeling of spatial correlations, while neglecting the fairly stable and recurrent nature of human mobility patterns. In this short paper, we show that a naive baseline method based on the average weekly pattern and linear regression can achieve comparable results to many state-of-the-art deep learning approaches for spatio-temporal forecasting in transportation, or even outperform them on several datasets, thus contrasting the importance of stationarity and recurrent patterns in the data with the importance of spatial correlations. Furthermore, we establish 9 different reference benchmarks that can be used to compare new approaches for spatio-temporal forecasting, and provide a discussion on best practices and the direction that the field is taking.