← Back to all news
arXiv AI By Jianing Long, Xiaobin Li, Wuming Lei, Weiguang Wang

When better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value

Read the original on arXiv AI →

The study examines why improved traffic forecasts do not always lead to better signal‑control outcomes. Using 29 days of reconstructed traffic data from Xuancheng, China, the authors evaluate various forecasting methods—including point forecasts, conformal intervals, and dependence‑aware scenarios—within a closed‑loop control framework. While entry‑level and movement‑level forecasts reduce mean absolute error by about 4%, the resulting signal‑control decisions sometimes worsen queue vehicle‑seconds and spillback exposure, highlighting gaps between forecast accuracy and operational benefit.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Oct 8

Evaluating Sequence Assembly Strategies for Differentially Private Synthetic Time-Series Forecasting

The paper investigates how post‑generation assembly of fixed‑length synthetic windows affects downstream forecasting performance. By varying overlap rates and window‑weighting schemes, the authors evaluate boundary continuity, statistical and temporal fidelity, and TSTR utility across four public datasets and five forecasting models. Results show that optimal assembly depends on the forecaster, with increased overlap improving continuity but not always reducing forecasting error, and provide assembly grids and TRTR references to quantify these effects.

By Guoxiong Long, Huizhen Huang, Qikun Cai, Tao Huang, Chen Hou
More like this →
arXiv AI
Oct 7

Joint upper-bound coverage and route-choice utility: an empirical evaluation on two urban proxy tasks

The paper investigates whether improving traffic forecast accuracy or increasing uncertainty coverage benefits route choice decisions. Using a frozen protocol on Beijing and Chengdu road speed data, the authors compare raw 90th‑percentile path time bounds with jointly calibrated upper bounds, finding that joint coverage improves from roughly 83% to 92% in Beijing and from 75% to 88% in Chengdu, yet this comes with higher lateness and travel time. A separate predictor comparison shows that reducing speed mean absolute error by 14.91% also reduces lateness by 1.46 percentage points, indicating that joint coverage alone is not a reliable proxy for downstream route utility in these offline tasks.

By Jianing Long, Xiaobin Li, Wuming Lei, Weiguang Wang
More like this →