An Efficient Two-stage Gradient Boosting Framework for Short-term Traffic State Estimation

TL;DR

This paper introduces a two-stage gradient boosting framework for real-time short-term traffic state estimation, leveraging sparse data and temporal features, achieving competitive results in the Traffic4cast challenge.

Contribution

The paper proposes an efficient two-stage gradient boosting approach that combines temporal feature derivation with traffic state prediction, improving performance and efficiency.

Findings

Achieved third place in Traffic4cast challenge

Demonstrated strong empirical performance

Maintained high efficiency in real-time estimation

Abstract

Real-time traffic state estimation is essential for intelligent transportation systems. The NeurIPS 2022 Traffic4cast challenge provides an excellent testbed for benchmarking short-term traffic state estimation approaches. This technical report describes our solution to this challenge. In particular, we present an efficient two-stage gradient boosting framework for short-term traffic state estimation. The first stage derives the month, day of the week, and time slot index based on the sparse loop counter data, and the second stage predicts the future traffic states based on the sparse loop counter data and the derived month, day of the week, and time slot index. Experimental results demonstrate that our two-stage gradient boosting framework achieves strong empirical performance, achieving third place in both the core and the extended challenges while remaining highly efficient. The source code for this technical report is available at \url{https://github.com/YichaoLu/Traffic4cast2022}.