A Metamodel for Estimating Error Bounds in Real-Time Traffic Prediction Systems

This paper presents a methodology for estimating the upper and lower bounds of a real-time traffic prediction system, i.e., its prediction interval. Without a very complex implementation work, this model is able to complement any preexisting prediction system with extra uncertainty information such as the 5% and 95% quantiles. The authors treat the traffic prediction system as a black box that provides a feed of predictions. Having this feed together with observed values, the authors then train conditional quantile regression methods that estimate the upper and lower quantiles of the error. The goal of conditional quantile regression is to determine a function, i.e., dᵀ(x), that returns the specific quantile τ of a target variable d, given an input vector x. Following Koenker, the authors implement two functional forms of dᵀ(x): locally weighted linear, which relies on value on the neighborhood of x, and splines, a piecewise defined smooth polynomial function. This methodology is demonstrated with three different traffic prediction models applied to two freeway data sets from Irvine, CA, and Tel Aviv, Israel. The results are contrasted with a traditional confidence intervals approach that assumes that the error is normally distributed with constant (homoscedastic) variance. The authors apply several evaluation measures based on earlier literature and contribute two new measures that focus on relative interval length and balance between accuracy and interval length. For the available data set, the authors verified that conditional quantile regression outperforms the homoscedastic baseline in the vast majority of the indicators.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01539265
  • Record Type: Publication
  • Files: TLIB, TRIS
  • Created Date: Sep 9 2014 3:27PM