← Back to all news
arXiv AI

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

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.

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 →
arXiv Machine Learning
Oct 9

RideBench: A Large-Scale Exogenous-Aware Benchmark for Ride-Hailing Time Series Forecasting

RideBench is a new benchmark built on a large-scale ride‑hailing time‑series dataset called Ride‑Hailing, which spans four years of half‑hourly data across 200 spatial areas and includes three exogenous scenarios: weather disturbance, holiday effect, and large‑scale event impact. The benchmark evaluates over 30 forecasting methods for both week‑ahead and 8‑week‑ahead horizons, revealing that while future‑known exogenous variables improve week‑ahead accuracy, current models still struggle with disturbance‑induced pattern changes and long‑horizon forecasting. These results highlight a mismatch between existing models and real‑world ride‑hailing needs, underscoring the necessity for better exploitation of exogenous information, scalability, and long‑horizon planning capabilities.

By Shengsheng Lin, Jing Hu, Zhengyang Hu, Jiazheng Sun, Zichun Cao, Siwei Sun, Zhichao Zou, Enyun Yu, Dongdong Li, Xinyi Hu, Weiwei Lin
benchmarks
More like this →
arXiv AI
Oct 5

Time Series Forecasting Benchmarks Need Scenario-Grounded Stress Testing

The paper argues that current time‑series forecasting benchmarks are too narrow, rewarding low held‑out error while failing to capture real‑world failure modes such as structured input anomalies, regime shifts, and sensor faults. It proposes scenario‑grounded stress testing, where each test includes historical data, future targets, a semantic scenario, a failure operator, and a difficulty level, to make evaluation interpretable and deployment‑relevant.

By Yuyang Zhao, Lian Xu, Hao Xue
benchmarkssafety
More like this →