# Deep Sequence Learning with Auxiliary Information for Traffic Prediction

Source: [Deep Sequence Learning with Auxiliary Information for Traffic Prediction](<https://www.sota2.com/research/paper/68fa647c1e209131cea04c12>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T02:57:38.769Z

Authors: Binbing Liao, Jingqing Zhang, Chao Wu, Douglas McIlwraith, Tong Chen, Shengwen Yang, Yike Guo, Fei Wu

Published: 2018-06-13T13:38:22.000Z

## Abstract

Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved. In this paper, we intend to improve traffic prediction by appropriate integration of three kinds of implicit but essential factors encoded in auxiliary information. We do this within an encoder-decoder sequence learning framework that integrates the following data: 1) offline geographical and social attributes. For example, the geographical structure of roads or public social events such as national celebrations; 2) road intersection information. In general, traffic congestion occurs at major junctions; 3) online crowd queries. For example, when many online queries issued for the same destination due to a public performance, the traffic around the destination will potentially become heavier at this location after a while. Qualitative and quantitative experiments on a real-world dataset from Baidu have demonstrated the effectiveness of our framework.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Traffic Speed Prediction on Q-Traffic (test)](<https://www.sota2.com/research/sota/traffic-speed-prediction-on-q-traffic-test.md>): Traffic Speed Prediction; Q-Traffic (test); Error (15 min): 4.52.

- [Traffic Speed Prediction on Q-Traffic event intervals (test)](<https://www.sota2.com/research/sota/traffic-speed-prediction-on-q-traffic-event-intervals-test.md>): Traffic Speed Prediction; Q-Traffic event intervals (test); MAPE (15-min): 4.61.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1806.07380>)

[PDF](<https://arxiv.org/pdf/1806.07380.pdf>)

[Implementation](<https://github.com/JingqingZ/BaiduTraffic>)