Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Pairwise Comparisons with Flexible Time-Dynamics
 
conference paper

Pairwise Comparisons with Flexible Time-Dynamics

Maystre, Lucas  
•
Kristof, Victor  
•
Grossglauser, Matthias  
January 1, 2019
KDD'19: Proceedings of the 25th ACM Sigkdd International Conferencce on Knowledge Discovery and Data Mining
25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD)

Inspired by applications in sports where the skill of players or teams competing against each other varies over time, we propose a probabilistic model of pairwise-comparison outcomes that can capture a wide range of time dynamics. We achieve this by replacing the static parameters of a class of popular pairwise-comparison models by continuous-time Gaussian processes; the covariance function of these processes enables expressive dynamics. We develop an efficient inference algorithm that computes an approximate Bayesian posterior distribution. Despite the flexbility of our model, our inference algorithm requires only a few linear-time iterations over the data and can take advantage of modern multiprocessor computer architectures. We apply our model to several historical databases of sports outcomes and find that our approach a) outperforms competing approaches in terms of predictive performance, b) scales to millions of observations, and c) generates compelling visualizations that help in understanding and interpreting the data.

  • Files
  • Details
  • Metrics
Type
conference paper
DOI
10.1145/3292500.3330831
Web of Science ID

WOS:000485562501029

Author(s)
Maystre, Lucas  
Kristof, Victor  
Grossglauser, Matthias  
Date Issued

2019-01-01

Publisher

ASSOC COMPUTING MACHINERY

Publisher place

New York

Published in
KDD'19: Proceedings of the 25th ACM Sigkdd International Conferencce on Knowledge Discovery and Data Mining
ISBN of the book

978-1-4503-6201-6

Start page

1236

End page

1246

Subjects

pairwise comparisons

•

ranking

•

time series

•

kalman filter

•

bayesian inference

•

sports

•

games

•

models

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
INDY1  
INDY2  
Event nameEvent placeEvent date
25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD)

Anchorage, AK

August 04-08, 2019

Available on Infoscience
October 5, 2019
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/161845
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés