Nonlinear Traffic Prediction as a Matrix Completion Problem with Ensemble Learning

Wenqing Li, Chuhan Yang, Saif Eddin Jabari

Research output: Contribution to journalArticlepeer-review


This paper addresses the problem of short-term traffic prediction for signalized traffic operations management. Specifically, we focus on predicting sensor states in high-resolution (second-by-second). This contrasts with traditional traffic forecasting problems, which have focused on predicting aggregated traffic variables, typically over intervals that are no shorter than five minutes. Our contributions can be summarized as offering three insights: first, we show how the prediction problem can be modeled as a matrix completion problem. Second, we use a block-coordinate descent algorithm and demonstrate that the algorithm converges in sublinear time to a block coordinate-wise optimizer. This allows us to capitalize on the “bigness” of high-resolution data in a computationally feasible way. Third, we develop an ensemble learning (or adaptive boosting) approach to reduce the training error to within any arbitrary error threshold. The latter uses past days so that the boosting can be interpreted as capturing periodic patterns in the data. The performance of the proposed method is analyzed theoretically and tested empirically using both simulated data and a real-world high-resolution traffic data set from Abu Dhabi, United Arab Emirates. Our experimental results show that the proposed method outperforms other state-of-the-art algorithms.

Original languageEnglish (US)
Pages (from-to)52-78
Number of pages27
JournalTransportation Science
Issue number1
StatePublished - 2022


  • Adaptive boosting
  • Adaptive control
  • Ensemble learning
  • High-resolution data
  • Kernel regression
  • Matrix completion
  • Signalized intersections
  • Sparse approximation
  • Traffic prediction

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Transportation


Dive into the research topics of 'Nonlinear Traffic Prediction as a Matrix Completion Problem with Ensemble Learning'. Together they form a unique fingerprint.

Cite this