Success in sport often requires making good decisions on complex issues, based on constantly changing information. Practitioners must recruit players based on predictions about their future performance potential, or design training programs and manage training to balance the need for performance improvements…
Success in sport often requires making good decisions on complex issues, based on constantly changing information. Practitioners must recruit players based on predictions about their future performance potential, or design training programs and manage training to balance the need for performance improvement with the need to maintain low injury risk. There are also complex decisions to be made about how to compete, regarding the technical and tactical aspects of the game. Although coaches are very capable of making good decisions based on their experience and opinions, these decisions could be improved if supported by evidence. Particularly given the increasing amount of new data sources that could be used to evaluate athletes, such complex decisions should be made based on the available evidence and experience contained in historical data.
Additionally, the decisions that can be supported are becoming increasingly granular, with coaches and support staff having to make numerous micro-decisions on a wide variety of issues daily, such as training load, plans tactics, scouting, etc. Optimizing sports performance becomes a matter of making as many micro-decisions as possible, based on substantial and detailed data, as well as well-founded machine learning methods. Part of this development is a move towards personalized modeling of sports performance. Sports science has already established different sports disciplines requiring different body types and appropriate training regimes (e.g. sprint or endurance training). However, personalization allows for much finer optimization, by exploiting individuals’ historical data to understand their specific strengths and weaknesses, for example in terms of injuries.
On a technical level, sports data offers an interesting test bed for data mining researchers. The sports data universe is not discrete, and elements of human individuality and human error have more influence, thus increasing the challenge for researchers. Yet at the same time, many sports are limited by rules and where the action takes place (track, field, rink, etc.), providing natural experiences and repeatability that other contexts lack real. Sports data is therefore very attractive for computational research to create new methods and apply them to a real-world problem.
In recent years, machine learning methods often provide a better opportunity to answer complex questions and discover unknown but important relationships within datasets. Although machine learning methods have been applied to sports data for many years, there is a constant need for method development and refinement as well as a better understanding of the implementation of artificial intelligence in the context sporty.
Artificial intelligence and machine learning methods can play a crucial role in sports practice in the future. They benefit the entire decision-making process by accelerating and automating information collection, highlighting information patterns, combining and simplifying large and complex data sets, enabling understandable visualization information and providing automated decision support.
Topics of interest in this research topic include:
• Solutions to data analysis problems associated with complex datasets in sports
• New approaches for automated information extraction from streaming data (such as event detection)
• Insights into the use of AI in sports practice
• Compare and contrast techniques to aid decision making in sport
• Exploration of ethical issues linked to the use of AI in sport
• Custom models for load monitoring and injury prevention
Keywords: Data science, data mining, machine learning, modeling, predictive analysis, pattern recognition
Important note: All contributions to this research topic must fall within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more appropriate section or journal at any stage of peer review.
