Graph-based Approaches for Analysing Team Interaction on the - PowerPoint PPT Presentation

Graph-based Approaches for Analysing Team Interaction on the Example of Soccer Markus Brandt and Ulf Brefeld Knowledge Mining & Assessment TU Darmstadt / DIPF brefeld@cs.tu-darmstadt.de

Motivation ๏ Team interaction important for playmaking, team strategy and thus also for winning ๏ BUT: interaction not covered well by counting- based approaches and descriptive statistics ๏ Here: use of Page rank to capture team interaction Ulf Brefeld brefeld@cs.tu-darmstadt.de 2

Representation pass-based receiver-based interaction-based ๏ Captures ๏ Importance of ๏ Importance of natural flow successful pass team interaction ๏ Receiver gets ๏ Credits for ๏ Credits for both the credits player who involved players passes the ball Ulf Brefeld brefeld@cs.tu-darmstadt.de 3

Chain Score ๏ Average length of chains a player p is involved in: Page Rank ๏ Normalised sum of page ranks of nodes pointing to p given by Ulf Brefeld brefeld@cs.tu-darmstadt.de 6

Empirical Results ๏ Bundesliga seasons 2009/10 - 2013/14 ๏ 1530 games, >250000 pass chains ๏ Player ranking ๏ Prediction of winning team distribution of chain lengths Ulf Brefeld brefeld@cs.tu-darmstadt.de 7

Top-ranked Players chain score page rank (pass) page rank (receiver) page rank (interaction) ๏ Chain score ranks players according to #chains ๏ Page rank captures team interaction + playmaking Ulf Brefeld brefeld@cs.tu-darmstadt.de 8

Preliminary Results train: 2009/10 - 2012/13, test 2013/14 #completed passes chain score page rank pass receive interact pass receive interact pass receive interact ๏ Baselines: home team: 47.39%, better team 52.94% ๏ 2 features (home and away team score) ๏ Chain score worst, completed passes and page rank perform similarly Ulf Brefeld brefeld@cs.tu-darmstadt.de 9

Conclusion ๏ Page rank captures team interaction and playmaking better than simple frequency-based approaches ๏ Representation depends on application at-hand (e.g., pass, receiver, interaction-based) ๏ Preliminary results for predicting winning teams show that counting-based baselines (#completed passes) perform similarly Ulf Brefeld brefeld@cs.tu-darmstadt.de 10

Graph-based Approaches for Analysing Team Interaction on the - PowerPoint PPT Presentation

Graph-based Approaches for Analysing Team Interaction on the Example of Soccer Markus Brandt and Ulf Brefeld Knowledge Mining & Assessment TU Darmstadt / DIPF brefeld@cs.tu-darmstadt.de Motivation Team interaction important for

Graph-based and Lexical-Syntactic Approaches for the Authorship Attribution Task Notebook for PAN

Approaches Based on guided code generation Based on exploring existing code Based on

Local Consistency Combinatorial Problem Solving (CPS) Enric Rodr guez-Carbonell (based on

Pregel Large-Scale Graph Processing William Jones Analysing large graphs is hard. We are

Developing Software Frameworks for Petascale and Beyond Using Dynamic Graph Based Approaches

Interaction-based knowledge evolution Small team (three permanent researchers); ome (

Beyond Macrobenchmarks Microbenchmark-based Graph Database Evaluation Matteo Lissandrini, Martin

Using Groove for analysing RPGame models Model Driven Engineering Brent van Bladel University of

Integration Testing Path Based Chapter 13 Call graph based integration Use the call graph

Cardi-OH ECHO - Hypertension Thursday, February 28, 2019 1 Team-based Care Approaches to

1 PageRank, TextRank, closeness, betweenness, NP chunks , An Overview of Graph-Based Keyword

Outline Gaze-Based Interaction in Cinematic 360 VR Cinematic 360 VR Gaze-Based

Outline Introduction Background Progress on the implementation of the MTSF

NRC Approaches to Interaction and Communication with the Public The NRC continually works

Graph-based Dependency Parsing (Chu-Liu-Edmonds algorithm) Sam Thomson (with thanks to Swabha

Week 5 Kullmann Analysing BFS Depth-first search Depth-first search Analysing DFS

Using R for analysing spatio-temporal datasets: Bigiarini a satellite-based precipitation case

Monitoring and analysing multilingual media reports Monitoring and analysing multilingual media

12) Validation of Graph-Based Datalog and EARS Transitive Closure Models

Analysing Switch-Case Tables by Partial Evaluation Niklas Holsti Tidorum Ltd www.tidorum.fi

3D Interaction with Virtual Environments based on Body and Brain Anatole Lcuyer (Inria)

Graph-based Clustering Transform the data into a graph representation Vertices are the

Applied Text Analytics the need for human information interaction and cognitive approaches in

Monitoring and Analysing Professional Speed Skaters 1 LottoNL-Jumbo Speed Skating Team Trainer: