Welcome
The Machine Learning and Data Mining for Sports Analytics workshop aims to bring people from outside of the Machine Learning and Data Mining community into contact with researchers from that community who are working on Sports Analytics. The 2018 workshop was co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Dublin, Ireland, and took place on Monday 10 September 2018. The accepted papers can be found in the conference proceedings.
Background
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 the popularity of sports betting. The developed techniques are being used for decision support in all aspects of professional sports, including:
- 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
The interest in the topic has grown so much that there is now an annual conference on Sports Analytics at the MIT Sloan School of Management, which has been attended by representatives from over 70 professional sports teams in eminent leagues such as the Major League Baseball, National Basketball Association, National Football League, National Hockey League, Major League Soccer, English Premier League, and the German Bundesliga. Furthermore, sports data providers such as OPTA have started making performance data publicly available to stimulate researchers who have the skills and vision to make a difference in the sports analytics community.
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 but there has been growing interest in the Machine Learning and Data Mining community in past years. Building off our successful workshops on Sports Analytics at ECML/PKDD 2013, ECML/PKDD 2015, ECML/PKDD 2016, and ECML/PKDD 2017, we want to keep the forward momentum by hosting a fifth 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.
To facilitate this, we have assembled a diverse program committee that includes statisticians, practitioners in sports-related matters, and Machine Learning and Data Mining researchers.