Machine Learning and Data Mining for Sports Analytics (Workshop @ ECML/PKDD 2018)

MLSA 2018


Data Mining & Analysis



Sports Analytics has been a steadily growing and rapidly evolving area over the last decade both in US professional sports leagues and in European football leagues. The recent implementation of strict financial fair-play regulations in European football will definitely increase the importance of Sports Analytics in the coming years. In addition, there is of course the popularity of sports betting. The developed approaches are being used for decision support in all aspects of professional sports, including:
- Analyzing positional data (tracking data)
- Match strategy, tactics, and analysis
- Player acquisition, player valuation, and team spending
- Training regimens and focus
- Injury prediction and prevention
- Performance management and prediction
- Match outcome and league table prediction
- Tournament design and scheduling
- Betting odds calculation
Traditionally, the definition of sports has also included certain non-physical activities, such as chess – in other words, games. Especially in the last decade, so-called e-sports, based on a number of computer games, have become very relevant commercially. Professional teams have been formed for games such as Starcraft 2, Defense of the Ancients (DOTA) 2, and League of Legends. Moreover, tournaments offer large sums of prize money and are important broadcast events. Given that topics such as strategy analysis and match forecasting apply in equal measure to these new sports (and other topics might apply as well but are not very well explored so far), and data collection is in fact somewhat easier than for off-line sports, we have chosen to broaden the scope of the workshop and solicit e-sports submissions as well.
The majority of techniques used in the field so far are statistical. However, there has been growing interest in the Machine Learning and Data Mining community about this topic. Building off our successful workshops on Sports Analytics at ECML/PKDD 2013, ECML/PKDD 2015, ECML/PKDD 2017, and ECML/PKDD 2017 we wish to continue to grow this interest by hosting a fourth edition at ECML/PKDD 2018. We think that the setting is interesting and challenging, and can potentially be a source of new data. Furthermore, we believe that this offers a great opportunity to bring people from outside of the Machine Learning community into contact with typical ECML/PKDD contributors as well as to highlight what the community has done and can
do in the field of Sports Analytics.
*Submissions*
The workshop solicits papers covering both predictive and descriptive Machine Learning, Data Mining, and related approaches to Sports Analytics settings, including, but not limited to, the list of topics above. Adopting a broad definition of sports, the workshop is also open to submissions on electronic sports (i.e., e-sports) that are related to any of these topics. The following types of papers can be submitted:
- Long papers will be 9 pages of content and an unlimited number of references in the Springer LNCS style and should report on novel, unpublished work that might not be quite mature enough for a conference or journal submission.
- Prediction challenge papers will be 6 pages in Springer LNCS style and should describe the approach that participants in our football pass prediction challenge have taken to produce their predictions.
- Extended abstracts will be 2 pages in Springer LNCS style and summarize recent publications fitting the workshop.
Paper submission should be done via the Easychair system at https://easychair.org/conferences/?conf=mlsa18
Each paper will be reviewed by at least two members of the Program Committee on the basis of technical quality, relevance, significance, and clarity. Submitting a paper to the workshop means that if the paper is accepted at least one author should present the paper at the workshop.
The workshop will include invited talks, a mix of oral and poster presentations for all accepted papers, and a discussion regarding the goals, limits, and desirability of Sports Analytics.