ArticlePDF Available

Applications of Artificial Intelligence in the Game of Football: The Global Perspective

Authors:

Abstract and Figures

Purpose: Football is a very dynamic and high paced game in which minutest detail may be the reason for a win or a loose, but the human eye sometimes fails to capture these small details. That's where Artificial Intelligence (AI) comes into the picture. Football has seen the onset of applications of AI in the last few years, but the scope of AI is still not clear. Also, the limitations of AI should also be familiar to the stakeholders of the game. The study explores the unknown side of AI in the game of Football. Methodology: The work is based on exploratory study on the applications of AI in the game of Football. The study tried to explore the various ways in which AI is applied in present and can be applied in future in the game of football. The study has also explored the limitations of using AI or any kind of machine interference in this beautiful game. Finally, the study identified the scope of further study under this topic. Findings: Overall, the study found that with the help of AI and other varied technologies, teams are able to discover new potential and achieve goals which were thought to be impossible before especially in enhancing team competitiveness, decision making and better customer experience. The technology is still immature and needs significant improvement. Implications: The study implies AI has been highly beneficial to the game of Football as a whole, but at the same time AI has not been completely utilised as per its capabilities. Originality: The study talks about some unprecedented applications of AI in football, and also talks about some unfamiliar limitations of AI.
Content may be subject to copyright.
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [18]
© 2020 ERM Publications
DOI : 10.18843/rwjasc/v11i2/03
DOI URL : http://dx.doi.org/10.18843/rwjasc/v11i2/03
Applications of Artificial Intelligence in the Game of Football:
The Global Perspective
Rathi Keshav,
Student,
School of Business and Management,
Christ (Deemed to be) University, India.
Koul Aditya V.,
Student,
School of Business and Management,
Christ (Deemed to be) University, India.
Somani Priyam,
Student,
School of Business and Management,
Christ (Deemed to be) University, India.
Dr. Manu K. S.,
Assistant Professor,
School of Business and Management,
Christ (Deemed to be) University, India.
(Received April 08, 2020; Accepted June 16, 2020)
ABSTRACT
Purpose: Football is a very dynamic and high paced game in which minutest detail may be
the reason for a win or a loose, but the human eye sometimes fails to capture these small
details. That’s where Artificial Intelligence (AI) comes into the picture. Football has seen the
onset of applications of AI in the last few years, but the scope of AI is still not clear. Also, the
limitations of AI should also be familiar to the stakeholders of the game. The study explores
the unknown side of AI in the game of Football. Methodology: The work is based on
exploratory study on the applications of AI in the game of Football. The study tried to explore
the various ways in which AI is applied in present and can be applied in future in the game of
football. The study has also explored the limitations of using AI or any kind of machine
interference in this beautiful game. Finally, the study identified the scope of further study
under this topic. Findings: Overall, the study found that with the help of AI and other varied
technologies, teams are able to discover new potential and achieve goals which were thought
to be impossible before especially in enhancing team competitiveness, decision making and
better customer experience. The technology is still immature and needs significant
improvement. Implications: The study implies AI has been highly beneficial to the game of
Football as a whole, but at the same time AI has not been completely utilised as per its
capabilities. Originality: The study talks about some unprecedented applications of AI in
football, and also talks about some unfamiliar limitations of AI.
Keywords: Artificial Intelligence, Football, Competitiveness, Decision making and Customer
experience.
INTRODUCTION:
Football is a team sport involving two competing teams of eleven field players each, and is considered the
most competitive sport in the world. The modern sport version originates in England, where in the mid-
19th century the rules were first published. Today, Millions of people around the world are watching and
playing soccer. Football is the most popular sport in the world with around 3.5 billion fans around the globe.
Football officially known as "Association Football" and in varied countries referred to as either soccer or
football is a team sport played between two teams, competing to get the ball into the other team's goal,
thereby scoring a goal. It was names association football to distinguish the sport from other forms of
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [19]
© 2020 ERM Publications
football. It is played by 250 million participants in more than 200 countries and addictions, making it the
most common sport in the world. The game is played according to codified rules known as the Law of the
Game established by the International Football Association Board (IFAB). The main governing body for
the sport worldwide is the International Federation of Association Football (FIFA). FIFA was founded in
1904 in France, headquartered in Switzerland with a motto of "For the Game. For the World". The FIFA
World Cup is the biggest international football competition organized by FIFA and hosted every four years
by different host nations. The first World Cup football competition was first held in Uruguay in 1930 and
the next World Cup football tournament will be hosted in Qatar in 2022, when 32 national teams will
compete for the championship. There are six confederations under FIFA which manages the game in the
different continents and regions of the world, i.e. Asian Football Confederation (AFC), Confederation of
African Football (CFA), Union of European Football Associations (UEFA), Confederation of North,
Central American & Caribbean Association Football (CONCACAF), Oceania Football Confederation
(OFC), South American Football Confederation (CONMEBOL) Approximately 200 countries compete in
the qualifying tournaments in their continental confederations to reach the final tournament, i.e. the FIFA
World Cup. In the world cup 32 national teams compete over a four-week period to become the world
champion. It is the most widely viewed and followed sporting event in the world, even more then the
Olympic Games. France was declared as the world champion in the 2018 FIFA World Cup (Men) hosted
by Russia, for the second time and United States was declared as the world champion in the 2019 FIFA
World Cup (Women) hosted by France, for the fourth time.
UEFA Champions League is considered to be the most esteemed competition in club football, in the recent
years it has been the most watched annual sporting event. Top division European clubs participate in this
tournament following the double round-robin system. Spanish clubs have the highest number of victories
followed by England and Italy. Real Madrid is the most successful club in the tournament's history winning
it for 13 times. Liverpool is the reigning champion of the UEFA Championship, 2019. Cristiano Ronaldo
a Portuguese footballer and a part of the Juventus club and Lionel Messi an Argentinian footballer, part of
the FC Barcelona club is considered to be the most decorated football players in the history of football.
The Ballon d'Or is considered one of the Football world's most prestigious honors. This honors the male
player considered to have done the best in the previous year based on votes from national teams ' football
journalists & coaches and captains. In 2019, Lionel Messi won 6 Ballon d'Or and Ronaldo won 5 times.
In terms of revenue and overall level of competition, Europe is the most prominent soccer market in the
world. Professional soccer in Europe had a total market value of US $25.5 billion in the 2016/17 soccer
season. The European Union or European Football Association (UEFA) is Europe's main governing body
for soccer, overseeing club and national competitions such as the clubs ' UEFA Champions League and the
national teams ' European Championship. The UEFA Champions League alone generated over two billion
Euros of total revenue in the 2016/17 season. Deloitte Sports Business Group's annual review of football
finance found that the "big five" leagues of Europe which are the leagues of England, Germany, Italy, Spain
and France; made a record £13.8 billion in revenue in 2017/18, which was a 6% increase from the previous
year. The demand for European football is now valued at £ 25.1 billion. The Premier League continues to
lead the way in revenue figures and is 72 per cent higher than its biggest rival, the Bundesliga in Germany.
German stadiums, however, remain the most attended in the European leagues, with an average attendance
for this current season of over 43,000.
Not only the prize money and broadcasting rights but the amount of sponsorships is also huge. The English
Premier League receives an estimated 50 million euros per season from its naming rights sponsor Barclays.
Kit / jersey sponsorship is an important revenue source for most European soccer clubs. The clubs at the
top-tier leagues in England, Spain, France, Germany, Italy and the Netherlands grossed more than EUR
500 million from kit sponsorships during the 2012/13 season. For example, the top Spanish team, FC
Barcelona receives about 30 million euros per season from its jersey sponsor, the Qatar Foundation. The
revenue from sponsorship, licensing and merchandising from the 2012 EURO in Poland and Ukraine
amounted to almost 300 million euros.
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [20]
© 2020 ERM Publications
Figure 1: Market size of the European football from 2006/07 to 2017/18 in billion €'s
Source: Statista's study on European Professional Football Market [15]
The sport continuously developing and evolving it has also resulting in emergence of some problems for
the sport. The major Problems and Challenges in the game of Football are as follows;
Competition:
It's almost a given, in the Premier League, that one of three or four teams will be crowned champions. The
season also plays out like a two-horse race. Every season in La Liga boils down to 2 teams. There is no
question that Football is boring at the highest level. You effectively know by halfway through the season
which two teams are going to fight for the championship. But football has become very boring even despite
the many exceptions to the law. Considering that - it'll only get worse. As more money is just flooding the
sport, a limited number of teams can only benefit from this. The increasing inflow of huge amounts of
money from the top football clubs has given them a financial muscle power to dominate the mid-table and
low budget teams.
Referees:
Referees frequently make incredibly difficult decisions that a lot of people would blame them for that
decision, whatever the result. But there is one truth which is undeniable. Referees are individual, and their
judgment is always affected by human error. Many close games have also been based not on which side
was the better but on a key decision that might have gone one way or another. Of course, not all blame can
be put on referees. Honest errors exist in any single career. No one can say that the noisy crowd doesn't
unconsciously affect him.
Tickets:
Some of the main issues from the supporter's viewpoint is that ticket prices are continually increasing. In
1991, a ticket to see Manchester United play Liverpool in the First Division cost just £ 5.50 which is £ 11.88
these days. Nowadays you're paying at least five or six times that price for a game of that nature and it
won't be long before most ordinary people can afford to go. Many people have already decided to avoid
joining their team because it's too costly and yet the rates seem only to continue to increase. Without the
fans in the crowd, football will be nothing and, sooner or later, the bubble would break.
Artificial Intelligence is a tool for thinking about how smart human thought is like a computer, robot or
product. AI is a study of how human brain thinks, learns, decides and works when attempting to solve
problems. And last but not least, this study builds smart software systems. AI seeks to enhance human
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [21]
© 2020 ERM Publications
intelligence-related computer features, such as reasoning, learning and problem-solving. AI is one of
Computer Science's fascinating and universal fields which will have a great future reach. AI is going to
allow a computer to act as a human being.
The intelligence is intangible. It is composed of Reasoning, Learning, Problem Solving, Perception, and
Linguistic Intelligence. The goals of AI research are reasoning, knowledge representation, planning,
learning, natural language processing, comprehension and object transfer and control capacity. There are
long term targets in the general intelligence sector. Approaches include mathematical, numerical, and
conventional AI coding approaches. Several techniques have been used during AI research concerning
search and mathematical optimization, artificial neural networks and methods based on statistics,
probability, and economics. Computer science attracts AI in science, maths, psychology, linguistics,
philosophy, etc. The major applications of AI as follows;
Gaming ? AI plays an important role for computer to think about a wide number of potential roles in
strategic games based on deep knowledge. Chess, river crossing and Football, for example.
Natural Language Processing ? Interaction with the computer that comprehends natural language
spoken by humans.
Expert Systems ? Machine or software provide explanation and advice to the users.
Vision Systems ? Systems understand, explain, and describe visual input on the computer.
Speech Recognition ? There are some AI based speech recognition systems have ability to hear and
express as sentences and understand their meanings while a person talks to it. For example, Siri and
Google assistant.
Handwriting Recognition? The handwriting recognition software read out the text written on paper and
recognize the shapes of the letters and transform it into editable text.
Intelligent Robots? Robots are able to perform the instructions given by a human.
Major Goals The major goals of the Artificial Intelligence Industry as a whole are Knowledge
reasoning, Planning Machine, Learning, Natural Language Processing, Computer Vision and Robotic
Applications.
Sports Investments in AI is paramount in today's world of game. There's been resistance to use some form
of technology in football for a long time. The Board of the International Football Association (IFAB) found
that the "beautiful game" did not require in-game decisions development assistance. Nonetheless, with
plenty of refereeing mistakes in major competitions like the 2010 FIFA World Cup, the IFAB decided to
take a re-look at how technology could assist referees in making the right decisions. Artificial Intelligence
and machine learning have gained a great deal of success in the field of football in recent years. AI has
come to be affiliated with football to predict match result. Through analyzing big data, machine learning
algorithms can predict the success of football games and their failure. Data scientists are now using AI to
help teams come up with spot scenarios and analytical interventions. AI-based, smart algorithms are
capable of simulating a wide number of events. This function helps analysts to analyze information
obtained from simulations. Such observations will help to make decisions on what is going to happen on
the pitch. This, in effect, helps coaches make educated choices about players as they plan for a game to
come. Through studying the historical data of the opponent, AI can be used to evaluate strategies that can
significantly aid in choosing and ultimately winning the best team for a specific game.
LITERATURE REVIEW:
A.C. Lapham & R.M. Bartlett (1995) found the important role that computer played in development of
experimental and theoretical sports biomechanics. They have mentioned the evolved role of Artificial
intelligence in today's era where AI is used for statistical modeling and simulation and optimization. In this
paper they have concentrated on the Decision-making done by AI through various methods and
observations made and comparisons tied with the biomechanical study of sports performance. McCabe, A.,
& Trevathan, J. (2008) pointed about the use of artificial intelligence for prediction of sporting outcomes.
They have included 5 sections, where first section talks about the "FORM" of the players. Section 2 gives
a background on the neural network engine used to make the predictions; Section 3 describes the raw data
used and the feature extraction process; Section 4 details the experiments conducted and the results of the
work, including comparisons to "expert" tipsters; future work is presented in Section 5. Novatchkov, H., &
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [22]
© 2020 ERM Publications
Baca, A (2013) have illustrated the potential of artificial intelligence (AI) techniques in sports on the
example of weight training. They have evaluated the pattern used for exercise on the weight training
machines. The data was produced through usage of force sensors attached to the machines. The results
showed good performance and predictive results, suggesting the viability and efficacy of AI techniques in
automatically assessing performance on weight training equipment and offering prompt advice to
sportsmen.
Xu, B. (2012) have investigated in prediction of Sports Performance based on Genetic Algorithm and
Artificial Neural Network. The data was collected through questionnaire and physical test of approx 1000
people. They have talked about the ANN and Genetic Algorithm in the paper and through the results
obtained by them, they concluded that it can approximately predict the value. As their prediction result and
original result were approximately same. De Silva et.al (2018) discussed about how decision making plays
a very critical role in game time situations and how it affects the result of the game. To improve decision
making they are introducing AI in collaboration with a very famous football club, Chelsea. This AI is based
on imitation learning, which means that it will learn from the experts and try to interpret the best possible
decision and the result if alternative decision was taken. Rodriguez, J (2019) discussed about the new
environment released by the google brain team known as the, Google Research Football which is based on
reinforcement learning in which the agents learn to play the game by simply playing it. It is further included
in an advanced football simulation environment, that helps in evaluating the varied reinforcement
algorithms. Kidd, R. (2019) pointed about decision making with the help of machines fed up with historical
data, for efficient decision making. Oloclip, a Madrid based company utilised AI to help clubs and players
make finest decisions but not with an aim to remove human decision making but to just assist them. Clubs
not agreeing to it are losing a big opportunity to improve and become better efficiently and effectively.
Ahmed, M. (2016) analyzed the potential of artificial intelligence in deciding players to transfer from one
club to another and their prospective value in the future. The KNN algorithm is best suited according the
research to identify the player and its value. This ultimately fills up the gap in the team and improves
decision making. Ratiu et.al (2010) investigated the developments in the use of Artificial Intelligence (AI)
in sports biomechanics. They discussed future applications of Expert Systems as diagnostic methods for
determining defects in sport movements. This also contrasts the sport techniques research, of which Expert
Systems has found no space to date, with the gait analysis, in which they are regularly used.
Robertson, S., & Joyce, D. (2019) discussed about how analytics has been applied at a far greater latitude
to all facets and kinds of business in sport. Applications included player management, injury recovery,
player fitness, player assessment, and game-day tactics. Manu Jha, M. S. (2019) discussed about AI and
machine learning have enabled faster and better decision-making in the world of sports such as football.
AI-powered algorithms can have actionable information that would bring even greater value to the players
and coaching staff. This also provides specifics such as the play style and formations of the opposing team,
the strategy they used in their previous matches, the pros and cons of each opponent, the tactics used by
their best players in tough situations etc. Carling et.al (2016) discussed the use technologies ranging from
GPS to automated camera tracking technology to collect data. As the physical demands of top leagues
around the world are rising year after year, the players ' physical efforts to gage power are now being placed
even more emphasis. Their research clearly revealed the particular physical profile for each distinct tactical
position that exists. Kelly et.al (2017) investigated the recent FIFA announcement directing each team in
the tournament could bring two computer tablets to collect data, assess decisions, and react to interactions
on the field. Data mining allows teams to evaluate complex data from the players and matches. Unlike
analyzing videos previously-played games, teams could get access to real-time information and analytics.
Rematas et.al (2018) highlighted that using deep learning systems, researchers from the University of
Washington, Facebook, and Google created a system that can take a YouTube soccer video and display it
in three dimensions using Augmented Reality (AR) devices or 3D viewers using AI and Hologram
technologies. The deep learning system aggregated and sorted the data to overlay positions and build the
depth needed for 3D displays in soccer game.
Application of AI in Football:
Artificial Intelligence (AI) is revolutionizing the sports industry in a very drastic and progressive way. It
exists in every aspect of a sport, devising a smarter way to victory with better efficiency and effectiveness
as compared to the human mind. Technology has become pervasive in the sports industry and a major
contributor towards the evolution of sport both inside and outside the stadium, deriving the best potential
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [23]
© 2020 ERM Publications
out of each team. Big data, Pattern Recognition, Machine Learning, Video Analysis are some of the
prominent technologies being used in the world of sports.
For a long period of time there was an ignorance towards using and kind of technology in football. The
IFAB deemed that the beautiful game of football didn't require the help of technology for in-game decisions.
But a lot of errors in referring in the 2010 World Cup, made the board revisit their take on technology
which would ultimately make the sport more competitive. AI-based intelligent algorithms have the
capability to simulate a large number of events. This feature enables analysts to translate insights derived
from the simulations.
JUST ADD AI, a German-based AI company, has helped win matches for a Bundesliga team by selecting
the right players. This has been done by the company developing an AI platform that collects information
from unstructured data and brings them into a single dashboard.
Picture 1: Referee using VAR at World Cup
Video Assistant Referee (VAR) is another major technology used in football and it was first incorporated
in the Laws of the Game by IFAB in 2018 after thorough trials at major events. VAR basically supports
decision making of referees by helping them in providing a review at the decisions made by the head referee
(Picture 1) [16]. It also helps in catching fouls which would otherwise go unnoticed by the referees. It has
99.3% accuracy and was used in the 2018 FIFA World Cup for the first time, which came to be known as
one of the cleanest world cups of all time.
Decision Accuracy Before and After VAR
(Study of 972 games worldwide)
Accuracy before VAR
93%
Accuracy after VAR
98.80%
Source: International Football Association Board's study
For assistance in referring the Goal Line Technology was introduced in 2012, which supported the decision
making of referee by telling him whether the ball has completely passed the goal line between the goal
posts and underneath the crossbar or not with a help of an electronic device behind the goal post and hence
assisting him in making his final decision (Picture 2). As it is an expensive technology it is only used at
major tournaments.
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [24]
© 2020 ERM Publications
Picture 2: Illustration of Goal-line technology
Telstar 18 (model of the football) with a Near Field Communication (NFC) chip was another landmark
technology used in the 2018 World Cup. NFC enabled users to have access to exclusive information
regarding the world cup and allows them to enter into a variety of competitions with the help of a smartphone.
Adidas introduced a miCoach smart ball (Picture 3), approved by FIFA that helps improve their dead ball
kicks. It tells the player the force with which the ball was hit, the trajectory of the ball, the spin and the exact
impact of the foot in connection with a smartphone, helping players in improving their performance.
Picture 3: Adidas miCoach smart ball
Big data along with machine algorithms are also used by analytics expert in various organizations that help them
in making predictions, team selection, betting etc. It helps the teams in understanding the pattern of playing of
the opponents through computer vision and imaging and deriving strategies to beat them on the field. Prediction
of injuries is another major factor of the sport which was solved through machine learning algorithms
Last year, a London based club tied up with an AI company named as "The Big Bang Fair" with an aim to
install an AI coach that could help the management in deciding the team's tactics and formations (Picture 4).
The AI learns through real time analysis of the game and suggests accordingly [17]. Leatherhead FC tied
up with IBM and is using the IBM Watson to improve the player and team performance for better results
in the league. IBM Watson provides all the necessary data to the management starting from video analysis,
statistical analysis, strategy formulation, opponent decoding etc.
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [25]
© 2020 ERM Publications
Picture 4: Watson used by Leatherhead F.C.
According to world football summit report of the year 2019, states that AI and Augmented Reality will
play a major role in the growth of the industry. Electronic Performance and Tracking System (EPTS) is
going to be used in the wearables of players to extract data that helps in better biomechanical and biological
analysis of the players. Virtual Reality (VR) and Augmented Reality (AR) will be the major reasons to
expand the viewership of the beautiful game to higher extents with a better experience. Esports and Fantasy
sport is going to be the next major trend. Esports is already on its way to become established as one of the
leading global sport. Fantasy sport market is also anticipated to grow at a drastic rate and will post a CAGR
of 11% by 2025.
The sports industry in general has lot in store to work on and improve, making it more competitive and
growth-oriented in nature.
How AI can solve the Problems and Challenges in the game of Football?
In the above section we discussed the existing applications of AI in football. Here, we will be discussing
about the possible use of AI in solving the unsolved problems and challenges in football (as discussed in
section 1.3).
Competition:
The top clubs continue to buy the best players in the transfer market by splurging chunks of money and the
other clubs have to settle with their second or third alternatives. As a result, the same set of teams continue
to challenge of the title. Using AI, the not so rich clubs can compete with the big clubs and keep their transfer
budget small at the same time. using AI can be used to automate repetitive and mundane tasks, so people
can focus on what they do best: complex problem solving, critical thinking, creativity and artistic expression.
Teams send scouts to other teams, drawing on their unparalleled expertise in finding new talent. Good
instinct is important. Teams have a large amount of records of such scouting that it has collected through
the years. The knowledge in these reports is gold, with insights into play style, work ethics, strengths and
weaknesses, team dynamics, and so on - all filtered through the talent scout's expert eye. AI can understand
scouting reports and extract the most relevant details, making them searchable and available for
visualization. By bringing all the data together into a cohesive picture for football teams, AI can provide a
very powerful combination that has the potential to up-level the game.
Referees:
While VAR has been officially adopted by FIFA to assist the on-field referee, the fact that AI can also
replace the side-line referees if not the on-field referees is not very far off. Dr Pearson - a futurologist for
tech site, Futurizon, said: "Developments in technology will mean that there will be possibilities for tech
to be introduced into sport to help benefit it, much like VAR. According to Dr Ian Pearson, football fans
will get used to seeing a robot linesman because AI is not prone to human error.
Robots are going to be better officiating because AI can make decisions more effectively, and quicker than
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [26]
© 2020 ERM Publications
the human mind will ever be. A machine can examine the video footage of each player on the field in real
time and it can decide whether two players come together and one of their feet meets the other person's
knee, or if the elbow meets the head or anything like that.
Picture 5: AI-Referee on side-lines
Robots and further advancements are also possible, however, whether it will be adopted by fans around the world.
Tickets:
To cope up with the increasing budgets and ambitious transfer targets the teams have increased the prices
of their matchday tickets and season tickets. The increasing ticket prices is a major concern for the
supporters of the sport making it increasingly difficult for the fans to go to the stadiums on weekly
matchdays. This has often resulted in leaving the stadium stands half-empty in predictable fixtures of the
team. The teams can develop a database with the variables such as past attendance, fixture difficulty,
average attendance, ticket prices, special occasions (such as first and last fixture of the season, Boxing Day,
first fixture after winter transfer window, etc.) and other such variables. Once a database is created, clubs
can use AI to predict an effective ticket prices well in advance.
SUMMARISED DISCUSSION:
Football is a internationally loved sport, with billions of fan base. It's a sport that inspires a great deal of
excitement and enthusiasm, and sport goings-on also represent problems concerning the broader human
condition. It is of course a sport which is about to be infused with artificial intelligence. AI has quickly
transformed technology and now it's making waves in nearly every industry. By making menial activities
more streamlined, it has the workloads for workers, freeing them for the specialties that need a human
touch. That is shifting the workforce from IT to football in every sector. With the global industry beginning
to sense the change to automation, AI and football are building a relationship that could change more than
just the way a sport is played. It wasn't until recently that teams were sanctioned to bring tablets on the
field for real-time data analysis. This could potentially mean, as FIFA gets more comfortable with tech on
the field, AI programs could be integrated for even faster real-time analysis in the future (Figure 6)
Whatever form of AI is used, it is evident that football is a sport that benefits from technical integration.
Whether it is used to preserve player health or help decide the best group of players for a game match, AI
is helping to change the football world as we know it. The future can bring many more surprises on the
horizon with the evolution of sport and technology.
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [27]
© 2020 ERM Publications
Picture 6: AI trying to predict the next action of the player
LIMITATIONS OF AI IN FOOTBALL:
Although the sport has benefited a lot with the overall use of AI but at the same time it also has some limitations.
High Cost:
AI in Football's hardware and software requirement is very expensive, because it needs tons of maintenance
to fulfill real world requirements. Maintenance Like VAR, there could be a significant purchasing expense
and a need for ongoing maintenance and repair. Goal Line Technology will also need frequent updates to
adapt to evolving regulations. The return on investment needs to be carefully considered by Football
Associations before applying it in football.
Can't think out of the box:
Even we are making smarter machines with AI, but they still can't work out of the box, because the robot
can only do the job they're being prepared for or programmed for. When football players seek new stuff,
learn skills and build their own gestures much of the time. They get better day by day also for Artificial
Intelligence which is hard to track.
No feelings and emotions:
AI machines can be an excellent artist, but they still don't have the sense that they can create some sort of
emotional connection to humans and can often be dangerous to users if they don't take proper care.
For example, in football there are times when a player performed very good in previous matches but due
to some personal problems which cause the player to be emotionally weak. But AI will not consider such
aspects and think that the player will keep on performing well according to the data AI has. But the player
is unable to perform cause of his emotional state
Increase dependency on machines:
With the increment of technology, people are getting more dependent on devices and hence they are losing
their mental capabilities. Which causes wrong decision by the team in real matches
No Original Creativity:
Because humans are so innovative and can envision some new ideas but even AI machines can't beat this
force of human imagination and can't be inventive and imaginative. Lack of Creativity: Creativity remains
an integral part of a good marketing strategy. Machines clearly lack the technical skills. Unlike machines,
humans can think and feel, which often guides their decision making when it comes to being creative.
So, just like the two faces of a coin, to reap the benefits of AI in football we must accept its limitations at
the same time.
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [28]
© 2020 ERM Publications
CONCLUSION
The future of the sports industry lies in the hand of technology. With the help of AI and other varied
technologies, teams are able to discover new potential and achieve goals which were thought to be
impossible before. The level of competitiveness has also elevated to a whole new level, due to better
understanding of the game and the players playing it. Decision making has become more factual based and
less based on emotions. AI is not only being used for in-stadium purposes but also for out-stadium purposes
which involves technology enabled stadiums, marketing and broadcasting using AI, providing customers
with a better experience etc. This evolution is taking place in all the sports and making the industry highly
vulnerable to its viewers and taking sports into a whole new level.
"The technology is still immature and needs significant improvement. It is far from a human level of
intelligence." Nothing is perfect, there are pros and cons to everything. Same way, there are certain
disadvantages of using AI. Like, increase in unemployment, it involves high costs to create, maintain and
repair the complex machines, performance of basic tasks is still not possible for AI, it delivers what is
coded in it so hence it is not able to understand and process the situation and take decision accordingly.
The scope of improvement in this industry is huge but it can only be achieved through determination,
patience and creative intellect.
Without a doubt we can say that artificial intelligence will make prediction of outcomes in the sports
industry reliable and certain to an extent. But it is important to understand that as long as human element
is involved in sports, there will always be unpredictability and uncertainty that makes it fascinating and
surprising for its viewers. As long as the element of surprise is there, the opportunity of profit will always
be there for businesses to exploit and earn from. The industry will never die and keep on improving with
time, making it highly competitive and dynamic in nature.
SCOPE FOR FURTHER STUDIES:
The current implementation of AI in football is at a very primary stage and football perceives to be area of
a very high potential for the development of AI. Our study focuses on the current use of Artificial
Intelligence in football which are mainly unilateral in nature i.e. focuses on only one side for e.g. refereeing,
management, etc. Further studies may explore applications of AI in areas which combines two or more
sides simultaneously such as application of AI on to predict the best possible playing 11 based on the
physical as well as tactical attributes of the players and the fixture difficulty of a match. In this way AI can
be used to predict the most suitable line up for the team and safe guarding the players from possible injuries
at the same time based on the need of the match and the qualities of the opposition. Further studies may
also involve other applications of technology and not just AI such as Big Data, Game Theory, etc for the
benefit of the game as a whole.
REFERENCES:
Ahmed, M. (2016). Can Artificial Intelligence Modelling Approaches Assist Football Clubs In Identifying
Transfer Targets, While Maintaining A Fair Transfer Market Using Player Performance Data?
(Doctoral dissertation, Cardiff Metropolitan University).
Carling, C., Bradley, P., McCall, A., & Dupont, G. (2016). Match-to-match variability in high-speed
running activity in a professional soccer team, Journal of Sports Sciences, 34(24), 2215-2223.
De Silva, V., Caine, M., Skinner, J., Dogan, S., Kondoz, A., Peter, T., ... & Smith, B. (2018). Player tracking
data analytics as a tool for physical performance management in football: A case study fro m
Chelsea football club academy, Sports, 6 (4), 130.
Jha, M. S. (2019). Can artificial intelligence (AI) win football & others sports matches. Retrieved from
https://www.mygreatlearning.com/blog/artificial-intelligence-can-win-football-matches/
Kelly, V. G., Leveritt, M. D., Brennan, C. T., Slater, G. J., & Jenkins, D. G. (2017). Prevalence, knowledge
and attitudes relating to β-alanine use among professional footballers, Journal of science and
medicine in sport, 20(1), 12-16.
Kidd, R. (2019). Man vs. Machine: Is soccer ready for artificial intelligence? Retrieved from
https://www.forbes.com/sites/robertkidd/2019/08/02/man-vs-machine-is-soccer-ready-for-
artificial-intelligence/
Lapham, A. C., & Bartlett, R. M. (1995). The use of artificial intelligence in the analysis of sports
- International Refereed Social Sciences Journal
E-ISSN: 2229-4686 ISSN: 2231-4172 http://www.researchersworld.com ■ Vol.–XI, Issue2, July 2020 [29]
© 2020 ERM Publications
performance: A review of applications in human gait analysis and future directions for sports
biomechanics, Journal of Sports Sciences, 13(3), 229-237.
McCabe, A., & Trevathan, J. (2008). Artificial intelligence in sports prediction, In Fifth International
Conference on Information Technology: New Generations (itng 2008) (pp. 1194-1197). IEEE.
Novatchkov, H., & Baca, A. (2013). Artificial intelligence in sports on the example of weight training,
Journal of Sports Science & Medicine, 12(1), 27.
Ratiu, O. G., Badau, D., Carstea, C. G., Badau, A., & Paraschiv, F. (2010). Artificial intelligence (AI) in
sports. In Proceedings of the 9th WSEAS international conference on Artificial intelligence,
knowledge engineering and data bases (pp. 93-97). World Scientific and Engineering Academy and
Society (WSEAS).
Rematas, K., Kemelmacher-Shlizerman, I., Curless, B., & Seitz, S. (2018). Soccer on your tabletop, In
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4738-4747).
Robertson, Samuel & Joyce, David. (2019). Bounded rationality revisited: Making sense of complexity in
applied sport science. 10.31236/osf.io/yh38j.
Rodriguez, J (2019). How Google uses reinforcement learning to train AI agents in the most popular sport
in the world, Retrieved from https://www.kdnuggets.com/2019/06/google-reinforcement-learning-
ai-agents-sport.html
Xu, B. (2012). Prediction of sports performance based on genetic algorithm and artificial neural network,
International Journal of Digital Content Technology and its Applications, 6(22), 141.
----
... As defended in [26], the future of team performance will be, more than ever before, based on data insights. Nonetheless, it is critical to comprehend that when a human component is associated with sport, there will always be unpredictability, making its outcome in general intriguing and surprising for its followers [27]. ...
Article
Full-text available
One of the great challenges for football coaches is to choose the football line-up that gives more guarantees of success. Even though there are several dimensions to analyse the problem, such as the opposing team characteristics. The objective of this study is to identify, based on the players’ physiological variables collected using Global Positioning Systems (GPS), which players are the most suitable to be part of the starting team/line-up. The work was developed in two stages, first with the choice of the most important variables using the Recursive Feature Elimination algorithm, and then using logistic regression on these chosen variables. The logistic regression resulted in an index, called the line-up preparedness index, for the following player positions: Fullbacks, Central Midfielders and Wingers. For the other players’ positions, the model results were not satisfactory.
... Specifically, the use of artificial intelligence is important for research in different fields of science, such as engineering, 29 education, 30 medicine, 31 marketing, 32 among others. [33][34][35] Its usage and development grew with the evolution of technology, being a critical tool to study large amounts of data that grow exponentially each year. 36,37 Moreover, machine learning and artificial intelligence offer great advantages in the aquaculture sector, 38,39 such as to assess water quality, 40 for ammonia nitrogen prediction, 41 to analyze the scute structure and sex identification, 42 to evaluate fish appetite, 43 for fish detection and behavior analysis, 44 and for intelligent feeding control. ...
Article
Full-text available
Aquaculture is a fundamental sector of the food industry nowadays. However, to become a sustainable and more profitable industry, it is necessary to monitor several associated parameters, such as temperature, salinity, ammonia, potential of hydrogen, nitrogen dioxide, bromine, among others. Their regular and simultaneous monitoring is expected to predict and avoid catastrophes, such as abnormal fish mortality rates. In this paper, we propose a novel anomaly detection approach for the early prediction of high fish mortality based on a multivariate Gaussian probability model. The goal of this approach is to determine the correlation between the number of daily registered physicochemical parameters of the fish tank water and the fish mortality. The proposed machine learning model was fitted with data from the weaning and pre-fattening phases of Senegalese sole (Solea senegalensis) collected over 2018, 2019, and 2020. This approach is suitable for real-time tracking and successful prediction of up to 80% of the high fish mortality rates. To the best of our knowledge, the proposed anomaly detection approach is the first time studied and applied in the framework of the aquaculture industry.
Article
Full-text available
There is growing on-going research into how footballer attributes, collected prior to, during and post-match, may address the demands of clubs, media pundits and gaming developers. Focusing upon individual player performance analysis and prediction, we examined the body of research which considers different player attributes. This resulted in the selection of 132 relevant papers published between 1999 and 2020. From these we have compiled a comprehensive list of player attributes, categorising them as static, such as age and height, or dynamic, such as pass completions and shots on target. To indicate their accuracy, we classified each attribute as objectively or subjectively derived, and finally by their implied accessibility and their likely personal and club sensitivity. We assigned these attributes to 25 logical groups such as passing, tackling and player demographics. We analysed the relative research focus on each group and noted the analytical methods deployed, identifying which statistical or machine learning techniques were used. We reviewed and considered the use of character trait attributes in the selected papers and discuss more formal approaches to their use. Based upon this we have made recommendations on how this work may be developed to support elite clubs in the consideration of transfer targets.
Chapter
Brazilian organizations must comply with the Brazilian General Data Protection Law (LGPD) and this need must be carried out in harmony with legacy systems and in the new systems developed and used by organizations. In this article we present an overview of the LGPD implementation process by public and private organizations in Brazil. We conducted a literature review and a survey with Information and Communication Technology (ICT) professionals to investigate and understand how organizations are adapting to LGPD. The results show that more than 46% of the organizations have a Data Protection Officer (DPO) and only 54% of the data holders have free access to the duration and form that their data is being treated, being able to consult this information for free and facilitated. However, 59% of the participants stated that the sharing of personal data stored by the organization is carried out only with partners of the organization, in accordance with the LGPD and when strictly necessary and 51% stated that the organization performs the logging of all accesses to the personal data. In addition, 96.7% of organizations have already suffered some sanction / notification from the National Data Protection Agency (ANPD). According to our findings, we can conclude that Brazilian organizations are not yet in full compliance with the LGPD.
Conference Paper
Full-text available
As football gained popularity and importance in the modern world, it been under greater scrutiny, so the industry must have better control of the train-ing sessions, and most importantly, the football games and their outcomes. With the purpose of identify the physiological variables of the players that most con-tribute to winning a football match, a study based on machine learning algorithms was conducted on a dataset of the players GPS positions during the football matches of a team from the 2nd division of the Portuguese championship. The findings reveal that the most important players’ physiological variables for pre-dicting a win are Player Load /min, Distance m/min, Distance 0.3m/s, Accelera-tion 0.2m/s with an accuracy of 79%, using the XGBoost algorithm.
Article
Full-text available
Background: Global positioning system (GPS) based player movement tracking data are widely used by professional football (soccer) clubs and academies to provide insight into activity demands during training and competitive matches. However, the use of movement tracking data to inform the design of training programmes is still an open research question. Objectives: The objective of this study is to analyse player tracking data to understand activity level differences between training and match sessions, with respect to different playing positions. Methods: This study analyses the per-session summary of historical movement data collected through GPS tracking to profile high-speed running activity as well as distance covered during training sessions as a whole and competitive matches. We utilise 20,913 data points collected from 53 football players aged between 18 and 23 at an elite football academy across four full seasons (2014–2018). Through ANOVA analysis and probability distribution analysis, we compare the activity demands, measured by the number of high-speed runs, the amount of high-speed distance, and distance covered by players in key playing positions, such as Central Midfielders, Full Backs, and Centre Forwards. Results and Implications: While there are significant positional differences in physical activity demands during competitive matches, the physical activity levels during training sessions do not show positional variations. In matches, the Centre Forwards face the highest demand for High Speed Runs (HSRs), compared to Central Midfielders and Full Backs. However, on average the Central Midfielders tend to cover more distance than Centre Forwards and Full Backs. An increase in high-speed work demand in matches and training over the past four seasons, also shown by a gradual change in the extreme values of high-speed running activity, was also found. This large-scale, longitudinal study makes an important contribution to the literature, providing novel insights from an elite performance environment about the relationship between player activity levels during training and match play, and how these vary by playing position.
Article
Full-text available
Objectives: To investigate β-alanine supplementation use and level of knowledge amongst professional footballers. Design: Cross-sectional survey of Australian professional football players. Methods: Questionnaires assessing β-alanine supplementation behaviours, level of knowledge and sources of information were completed by professional rugby union (RU) (n=87), rugby league (RL) (n=180) and Australian Rules Football (ARF) (n=303) players. Results: Approximately 61% of athletes reported β-alanine use, however use by ARF football players (44%) was lower than that of RU (80%) and RL players (80%). The majority of respondents were not using β-alanine in accordance with recommendations. Only 35% of the participants were able to correctly identify the potential benefits of β-alanine supplementation. The main information sources that influenced players' decision to use β-alanine were strength and conditioning coach (71%) and dietitian (52%). Forty-eight per cent of athletes never read labels prior to supplementing and only 11% completed their own research on β-alanine. Compared to RL and ARF players, RU players had both a greater knowledge of β-alanine supplementation and better supplementation practices. Conclusions: Despite over half the surveyed professional footballers using β-alanine, the majority of athletes used β-alanine in a manner inconsistent with recommendations. A better understanding of the environment and culture within professional football codes is required before supplement use becomes consistent with evidence based supplement recommendations.
Article
Full-text available
The overall goal of the present study was to illustrate the potential of artificial intelligence (AI) techniques in sports on the example of weight training. The research focused in particular on the implementation of pattern recognition methods for the evaluation of performed exercises on training machines. The data acquisition was carried out using way and cable force sensors attached to various weight machines, thereby enabling the measurement of essential displacement and force determinants during training. On the basis of the gathered data, it was consequently possible to deduce other significant characteristics like time periods or movement velocities. These parameters were applied for the development of intelligent methods adapted from conventional machine learning concepts, allowing an automatic assessment of the exercise technique and providing individuals with appropriate feedback. In practice, the implementation of such techniques could be crucial for the investigation of the quality of the execution, the assistance of athletes but also coaches, the training optimization and for prevention purposes. For the current study, the data was based on measurements from 15 rather inexperienced participants, performing 3-5 sets of 10- 12 repetitions on a leg press machine. The initially preprocessed data was used for the extraction of significant features, on which supervised modeling methods were applied. Professional trainers were involved in the assessment and classification processes by analyzing the video recorded executions. The so far obtained modeling results showed good performance and prediction outcomes, indicating the feasibility and potency of AI techniques in assessing performances on weight training equipment automatically and providing sportsmen with prompt advice.
Conference Paper
Full-text available
This paper presents an extension of earlier work in the use of artificial intelligence for prediction of sporting out- comes. An expanded model is described, as well as a broadening of the area of application of the original work. The model used is a form of multi-layer perceptron and it is presented with a number of features which attempt to capture the quality of various sporting teams. The system performs well and compares favourably with human tipsters in several environments. A study of less rigid “World Cup” formats appears, along with extensive live testing results in a major international tipping competition.
Article
This study investigated variability in competitive high-speed running performance in an elite soccer team. A semi-automated tracking system quantified running performance in 12 players over a season (median 17 matches per player, 207 observations). Variability (coefficient of variation [CV]) was compared for: total sprint distance (TSD, >25.2 km/h), high-speed running (HSR, 19.8-25.2 km/h), total high-speed running (THSR, ≥19.8 km/h); THSR when the team was in and out of ball possession, in individual ball possession, in the peak 5-min activity period; and distance run according to individual maximal aerobic speed (MAS). Variability for % declines in THSR and distance covered at ≥80% MAS across halves, at the end of play (final 15-min versus mean for all 15-min periods), and transiently (5-min period following peak 5-min activity period) was analysed. Collectively, variability was higher for TSD versus HSR and THSR and lowest for distance run at ≥80% MAS (CVs: 37.1%, 18.1%, 19.8% and 11.8%). THSR CVs when the team was in/out of ball possession, in individual ball possession and during the peak 5-min period were 31.5%, 26.1%, 60.1% and 23.9%. Variability in THSR declines across halves, at the end of play and transiently, ranged from 37.1%-142.6%, while lower CVs were observed in these metrics for running at ≥80% MAS (20.9%-53.3%).These results cast doubt on the appropriateness of general measures of high-speed activity for determining variability in an elite soccer team although individualisation of high-speed running thresholds according to fitness characteristics might provide more stable indicators of running performance and fatigue occurrence.
Article
This paper reviews developments in the use of Artificial Intelligence (AI) in sports biomechanics. It outlines possible uses of Expert Systems as diagnostic tools for evaluating faults in sports movements (techniques) and presents some example knowledge rules for such an expert system. It then compares the analysis of sports techniques, in which Expert Systems have found little place to date, with gait analysis, in which they are routinely used. Consideration is then given to the use of Artificial Neural Networks (ANNs) in sports biomechanics, focusing on Kohonen self-organizing maps, which have been the most widely used in technique analysis, and multi-layer networks, which have been far more widely used in biomechanics in general. Examples of the use of ANNs in sports biomechanics are presented for javelin and discus throwing, shot putting and football kicking. I also present an example of the use of Evolutionary Computation in movement optimization in the soccer throw in, which predicted an optimal technique close to that in the coaching literature. After briefly over viewing the use of AI in both sports science and biomechanics in general, the article concludes with some speculations about future uses of AI in sports biomechanics.
Article
Computers have played an important supporting role in the development of experimental and theoretical sports biomechanics. The role of the computer now extends from data capture and data processing through to mathematical and statistical modelling and simulation and optimization. This paper seeks to demonstrate that elevation of the role of the computer to involvement in the decision-making process, through the use of artificial intelligence techniques, would be a potentially rewarding future direction for the discipline. In the absence of significant previous work in this area, this paper reviews experiences in a parallel field of medical informatics, namely gait analysis. Research into the application of expert systems and neural networks to gait analysis is reviewed, observations made and comparisons drawn with the biomechanical analysis of sports performance. Brief explanations of the artificial intelligence techniques discussed in the paper are provided. The paper concludes that the creation of an expert system for a specific well-defined sports technique would represent a significant advance in the development of sports biomechanics.
Can Artificial Intelligence Modelling Approaches Assist Football Clubs In Identifying Transfer Targets, While Maintaining A Fair Transfer Market Using Player Performance Data? (Doctoral dissertation
  • M Ahmed
Ahmed, M. (2016). Can Artificial Intelligence Modelling Approaches Assist Football Clubs In Identifying Transfer Targets, While Maintaining A Fair Transfer Market Using Player Performance Data? (Doctoral dissertation, Cardiff Metropolitan University).