• Fitness & Health
• Sport & Exercise Science
• Physical Education
• Strength & Conditioning
• Sports Medicine
• Sport Management
• Dance

Machine learning: The cornerstone of data-driven decision making for sport organizations

This is an excerpt from Research Methods and Design in Sport Management-3rd Edition by Damon P.S. Andrew,Paul M. Pedersen.

By James Du, PhD, Yoseph Mamo, PhD, Bradley J. Baker, PhD

The field of sport management research has experienced a significant surge in the application of machine learning (ML; Du et al., 2024). This branch of artificial intelligence, designed to streamline and automate statistical learning processes, is increasingly becoming a cornerstone of data-driven decision making within the sport management domain (Mamo, 2023). By leveraging algorithms that learn from big data, discern patterns, and generate actionable insights, sophisticated decisions are now being executed with minimal reliance on human oversight.

While the roots of machine learning can be traced back to the 1950s when computer scientists first sought to create self-learning programs, recent technological breakthroughs have significantly expanded its usability. These advancements have made machine learning more practical, accessible, and relevant to the sport industry, empowering sport managers and scholars to harness diverse data sets for strategic advantage. To remain competitive, sport managers must navigate an increasingly complex landscape that demands not only operational efficiency but also strategic foresight. Machine learning, for instance, offers solutions that enable more precise customer targeting, refined marketing and sales forecasting, and greater fan engagement.

Watanabe et al. (2021) highlight that the integration of big data and artificial intelligence (AI) within sports extends beyond traditional areas such as performance metrics, talent scouting, or game analytics. In fact, a significant transformation is occurring on the business front, where sport organizations are increasingly adopting machine learning strategies to understand their fanbase and refine consumer preference profiles. As sport managers navigate this evolving landscape, it is becoming increasingly challenging for sport management scholars to ignore the vast opportunities presented by the proliferation of big data and the advancements in machine intelligence (Naraine and Wanless, 2020).

Far from being merely analytical tools, machine learning offers a transformative potential for research in sport management. Scholars now recognize that this analytical tool can be leveraged to tackle complex questions that were previously beyond reach. The true value of machine learning lies not only in its capacity for data analysis, but also in its ability to merge theoretical frameworks with cutting-edge computational methods, thereby deepening our understanding and driving the next wave of knowledge creation (Mamo et al., 2022).

OVERVIEW OF MACHINE LEARNING IN SPORT MANAGEMENT RESEARCH

A Primer in Machine Learning (ML)

The term “machine learning” (ML) is frequently misunderstood and used interchangeably with notions of highly advanced systems that mimic human cognition and consciousness. However, this oversimplification distorts the reality of what ML truly entails. Machine learning is a transformative branch of artificial intelligence that enables systems to learn from data, identify patterns, and make decisions with minimal human intervention. At its core, machine learning involves deriving insights from data and refining procedures, either autonomously or with limited human oversight (Khine, 2024). Though the term evokes images of sophisticated artificial intelligence, its real-world applications are far more routine and narrowly focused. One of the most familiar examples of ML’s integration into sports is the recommendation engines that power fan experiences on social media platforms.

Originating in the early 1950s, machine learning represents an evolution of artificial intelligence (AI), which refers to the development of computer systems capable of performing tasks that typically require human intelligence. AI aims to replicate human cognitive tasks through automation (Chollet, 2018). Early pioneers in the field believed that replicating human-level intelligence was a matter of crafting a detailed set of algorithms based on explicit knowledge, known as symbolic AI. Despite its promise, symbolic AI struggled to effectively address complex, ambiguous challenges such as image classification, speech recognition, and text processing. It was out of these limitations that machine learning emerged, redefining the landscape of artificial intelligence and ushering in a new era of technological advancement.

More Excerpts From Research Methods and Design in Sport Management-3rd Edition

---