Sports Data Analytics: A Case Study of off-Field Behavior of Players
The field of sports science is highly emerging and has made the headlines in the research and development activities, with new challenges and trends in the recent past. Sports analytics is the analysis of historical big data mainly available in the form of statistics to provide a proper insight into the entire team, an individual, or even the coach. It also facilitates decision-making for both on-field and off-field performances of all the concerned. The term “sports analytics” was popularized in 2011. It has also created a platform under the confluence of many disciplines such as data mining, machine learning, big data analytics, artificial intelligence, and predictive analytics. The paper aims at analyzing the off-field behavior of players using a statistical approach. The focus of the study is to comprehend the nature of data set, explore the relation between the attributes of the data set, and create a model to understand how the data relates to the underlying population using a real world data set. It comprises motion sensor data of 19 activities among both male and female categories. The sports data set is referred from the UCI repository. It consists of motor sensor data collected for both male and female players. The data set also clearly displays the three dimensions of big data namely, volume, variety, and veracity.
KeywordsSports data analytics Predictive analytics Big data Players behavior Recurrent neural network LSTM
The authors wish to acknowledge the UCI Machine Learning repository, Centre for Machine Learning, and Intelligent Systems for providing the data set.
- 3.Takahashi, M., Ikeya, K., Kano, M., Ookubo, H., & Mishina, T. (2016). Robust volleyball tracking system using multi-view cameras. In 2016 23rd International Conference on Pattern Recognition Pattern Recognition (ICPR) (pp. 2740–2745).Google Scholar
- 6.Baumer, B., Jensen, S., & Matthews, G. (2015). openWAR: An open source system for evaluating overall player performance in major league baseball. Journal of Quantitative Analysis in Sports, 11(2), 69–84. Retrieved October 31, 2018 from https://doi.org/10.1515/jqas-2014-0098.
- 12.https://archive.ics.uci.edu/ml/datasets/daily+and+sports+activities (accessed on 10–11-2018).
- 15.Altun, K., & Barshan, B. (2010). Human activity recognition using inertial/magnetic sensor units. In Proceedings First International Workshop on Human Behavior Understanding (in conjunction with the 20th International Conference on Pattern Recognition), August 22, 2010. Istanbul, Turkey,Google Scholar