Need A Boost? A Comparison of Traditional Commuting Models with the XGBoost Model for Predicting Commuting Flows (Short Paper)

Authors April Morton, Jesse Piburn, Nicholas Nagle

Thumbnail PDF


  • Filesize: 394 kB
  • 7 pages

Document Identifiers

Author Details

April Morton
  • Oak Ridge National Laboratory, 1 Bethel Valley Road, Oak Ridge, TN 37830, USA
Jesse Piburn
  • Oak Ridge National Laboratory, 1 Bethel Valley Road, Oak Ridge, TN 37830, USA
Nicholas Nagle
  • Department of Geography, University of Tennessee, Knoxville, 1000 Phillip Fulmer Way, Knoxville, TN 37916, USA

Cite AsGet BibTex

April Morton, Jesse Piburn, and Nicholas Nagle. Need A Boost? A Comparison of Traditional Commuting Models with the XGBoost Model for Predicting Commuting Flows (Short Paper). In 10th International Conference on Geographic Information Science (GIScience 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 114, pp. 51:1-51:7, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Commuting models estimate the number of commuting trips from home to work locations in a given area. Since their infancy, they have been increasingly used in a variety of fields to reduce traffic and pollution, drive infrastructure choices, and solve a variety of other problems. Traditional commuting models, such as gravity and radiation models, typically have a strict structural form and limited number of input variables, which may limit their ability to predict commuting flows as well as machine learning models that might better capture the complex dynamics of the commuting process. To determine whether machine learning models might add value to the field of commuter flow prediction, we compare and discuss the performance of two standard traditional models with the XGBoost machine learning algorithm for predicting home to work commuter flows from a well-known United States commuting dataset. We find that the XGBoost model outperforms the traditional models on three commonly used metrics, indicating that machine learning models may add value to the field of commuter flow prediction.

Subject Classification

ACM Subject Classification
  • Applied computing → Law, social and behavioral sciences
  • Machine learning
  • commuting modeling


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads


  1. Ethem Alpaydin. Introduction to machine learning. MIT Press, 2014. Google Scholar
  2. United States Census Bureau. Block group shapefiles for Tennessee [data file], 2010. URL:
  3. United States Census Bureau. LEHD Origin-destination employment statistics [dataset], 2010. URL:
  4. Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 785-794. ACM, 2016. Google Scholar
  5. Andrea De Montis, Marc Barthélemy, Alessandro Chessa, and Alessandro Vespignani. The structure of interurban traffic: a weighted network analysis. Environment and Planning B: Planning and Design, 34(5):905-924, 2007. Google Scholar
  6. Sven Erlander and Neil F Stewart. The gravity model in transportation analysis: theory and extensions, volume 3. VSP, 1990. Google Scholar
  7. Maxime Lenormand, Aleix Bassolas, and José J Ramasco. Systematic comparison of trip distribution laws and models. Journal of Transport Geography, 51:158-169, 2016. Google Scholar
  8. Celik H Murat. Sample size needed for calibrating trip distribution and behavior of the gravity model. Journal of Transport Geography, 18(1):183-190, 2010. Google Scholar
  9. Caleb Robinson and Bistra Dilkina. A machine learning approach to modeling human migration. arXiv preprint arXiv:1711.05462, 2017. Google Scholar
  10. Jan Rouwendal and Peter Nijkamp. Living in two worlds: a review of home-to-work decisions. Growth and Change, 35(3):287-303, 2004. Google Scholar
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail