• Publications
  • Influence
Markov Network Structure Learning: A Randomized Feature Generation Approach
TLDR
We present GSSL, a two-step approach to Markov network structure learning. Expand
  • 61
  • 7
  • PDF
Actions Speak Louder than Goals: Valuing Player Actions in Soccer
TLDR
This paper introduces (1) a new language for describing individual player actions on the pitch and a framework for valuing any type of player action based on its impact on the game outcome while accounting for the context in which the action happened. Expand
  • 45
  • 4
  • PDF
TODTLER: Two-Order-Deep Transfer Learning
TLDR
In this paper, we address this issue by regarding transfer learning as a process that biases learning in a target domain in favor of patterns useful in a source domain. Expand
  • 17
  • 4
  • PDF
Automatic Discovery of Tactics in Spatio-Temporal Soccer Match Data
TLDR
We describe a data-driven approach for identifying patterns of movement that account for both spatial and temporal information which represent potential offensive tactics. Expand
  • 25
  • 2
STARSS: A Spatio-Temporal Action Rating System for Soccer
TLDR
This paper presents an approach for automatically rating the actions performed by soccer players based on historical match data. Expand
  • 14
  • 2
  • PDF
Predicting Soccer Highlights from Spatio-Temporal Match Event Streams
TLDR
We propose the POGBA algorithm for automatically predicting highlights in soccer matches from spatiotemporal data, which is an important task that has not yet been addressed. Expand
  • 34
  • 1
Lifted generative learning of Markov logic networks
TLDR
We investigate generative learning where the goal is to maximize the likelihood of the model given the data. Expand
  • 29
  • 1
  • PDF
Machine Learning and Data Mining for Sports Analytics
TLDR
We introduce completion and scoring maps for the visualization of location- based location-based data to help capture high-level strategy. Expand
  • 25
  • 1
  • PDF
Analyzing Volleyball Match Data from the 2014 World Championships Using Machine Learning Techniques
TLDR
This paper proposes a relational-learning based approach for discovering strategies in volleyball matches based on optical tracking data, and are able to identify several interesting and relevant strategies. Expand
  • 12
  • 1
  • PDF
Automatically Discovering Offensive Patterns in Soccer Match Data
TLDR
We propose an inductive logic programming approach that can easily deal with the relational structure of the data. Expand
  • 21
...
1
2
3
4
...