The Quo Vadis submission at Traffic4cast 2019

TL;DR

This paper describes the Quo Vadis team's approach to the Traffic4cast 2019 challenge, using a temporal regression model with biases to incorporate seasonal patterns, achieving competitive results.

Contribution

Introduces a simple, efficient temporal regression model with biases for traffic prediction, and explores spatial correlation incorporation with limited success.

Findings

Biases improve model performance

Spatial correlations did not enhance results

Achieved 8th place in competition

Abstract

We describe the submission of the Quo Vadis team to the Traffic4cast competition, which was organized as part of the NeurIPS 2019 series of challenges. Our system consists of a temporal regression module, implemented as $1\times1$ 2d convolutions, augmented with spatio-temporal biases. We have found that using biases is a straightforward and efficient way to include seasonal patterns and to improve the performance of the temporal regression model. Our implementation obtains a mean squared error of $9.47\times 10^{-3}$ on the test data, placing us on the eight place team-wise. We also present our attempts at incorporating spatial correlations into the model; however, contrary to our expectations, adding this type of auxiliary information did not benefit the main system. Our code is available at https://github.com/danoneata/traffic4cast.