A Dockerized Big Data Architecture for Sports Analytics

Yavuz Melih Özgüven1, Utku Gönener2 and Süleyman Eken3

  1. Kocaeli University, Department of Computer Engineering
    Izmit 41001, Turkey
    yavuzozguven@hotmail.com
  2. Kocaeli University, Faculty of Sports Sciences
    Izmit 41001, Turkey
    utku.gonener@kocaeli.edu.tr
  3. Kocaeli University, Department of Information Systems Engineering
    Izmit 41001, Turkey
    suleyman.eken@kocaeli.edu.tr

Abstract

The big data revolution has had an impact on sports analytics as well. Many large corporations have begun to see the financial benefits of integrating sports analytics with big data. When we rely on central processing systems to aggregate and analyze large amounts of sport data from many sources, we compromise the accuracy and timeliness of the data. As a response to these issues, distributed systems come to the rescue, and the MapReduce paradigm holds promise for largescale data analytics. We describe a big data architecture based on Docker containers with Apache Spark in this paper. We evaluate the architecture on four data-intensive case studies in sport analytics including structured analysis, streaming, machine learning approaches, and graph-based analysis.

Key words

big data, sports analytics, containers, wearable devices, IoT, reproducible research

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS220118010O

How to cite

Özgüven, Y. M., Gönener, U., Eken, S.: A Dockerized Big Data Architecture for Sports Analytics. Computer Science and Information Systems, https://doi.org/10.2298/CSIS220118010O