ABSTRACT

In the game of football (soccer), the evaluation of players for transfer, scouting, squad
formation and strategic planning is important. However, due to the vast pool of grassroots
level player, short career span, differing performance throughout the individual’s career,
differing play conditions, positions and varying club budgets, it becomes difficult to
identify the individual player's performance value altogether. Our Player Performance
Prediction system aims at solving this complex problem analytically and involves learning
from various attributes and skills of a football player. It considers the skill set values of the
football player and predicts the performance value, which depicts the scope of
improvement and the capability of the player. The objective of this system is to help the
coaches and team management at the grassroots as well as higher levels to identify the
future prospects in the game of football without being biased to subjective conditions like
club budget, competitiveness in the league, and importance of the player in the team or
region. Our system is based on a data-driven approach and we train our models to generate
an appropriate holistic relationship between the players’ attributes values, market value and
performance value to be predicted. These values are dependent on the position that the
football player plays in and the skills they possess.
 TABLE OF CONTENTS

CHAPTER NO. TITLE Page No

ABSTRACT
LIST OF FIGURES
LIST OF ABBREVIATIONS

1. INTRODUCTION 07
1.1 problem statement 08
1.2 Decision tree 09
1.3 Boost algorithm 10

2. LITERATUTE SURVEY 11

2.1 predicting student performance

11
2.2 Chess game result prediction 12
2.3 sports event prediction
13

3. SYSTEM REQUIREMENTS 15
3.1 Software Requirements 15
3.2 Hardware Requirements 16

4. SYSTEM ANALYSIS 19
4.1 purpose 19
4.2 scope
19
4.3 Existing system
20
4.4 proposed system
21
5. MODULE DESCRIPTION 28
5.1 Data Collection 28
5.2 pre-processing 28
5.3 prediction module 29

6 SYSTEM ARCHITECTURE 30
7.1 system architecture 30
7.2 problem statement 31

7 CONCLUSION 38

8 SOURCE CODE 40
 CHAPTER 1
INTRODUCTION
Football, also known as soccer to the western part of the world, is a team based
sport played between two teams, each consisting of eleven players with a
spherical ball. This sport is played in over 200 countries and in almost all
weather conditions such as snow, rain, summer, etc. Football is governed by
FIFA (Fédération Internationale de Football Association) as the highest body
and further divides into various other bodies depending on the region and
nationality. The competitiveness of the game varies from region to region based
on the participation of the people, media coverage, and club budget. This, in
turn, brings varying differences in the level of players and also fluctuates the
market value and the skill level based on region, hype generated by the media,
competitiveness of the league in which they play and their experience. The
bigger the role the player plays in his team, the more likely they may be valued
in the market like being the finest penalty taker, or spot free kick specialist, or
other roles such as being a playmaker, chance creator, having excellent speed,
etc. In India, despite the decrease in the youth participation in sports,
particularly in the past few decades, the industry is putting in various means and
efforts to improve the sports environments in the form of grassroots level
programs, facilities, tournaments, coaching, public awareness, scholarships, etc.
The problem however lies in the fact that it’s difficult to search, analyze and
coach the players in every part of the country; especially in rural India which
consists of 70 percent of the 1.25 billion people approximately. To overcome
this difficulty the clubs recruit scouts of vast experience and regional
understanding to identify players. The AIFF is trying to improve the situation
by collaborating with various clubs and companies that make it possible to
teach the coaches who may be inexperienced by bringing in connecting sessions
with the experienced ones, hosting various tournaments at school, city, district,
state level, establishing football academies and community initiatives. The
proposed model is aimed specifically at the grassroot level players of India,
further scaling to other soccer leagues. The system is trained as per the in-game
values of the 2017 version of EA Sports FIFA. The reason for choosing values
based on a game is that it seemed to be the only source for a reliable, near
accurate and open form of data available for football players spanning across
several leagues. Moreover, the very nature of the game being a team based sport
makes it difficult to analyze the players due to their dependencies on the skill-
set of other team members, varying positions, formations, club budget,
competitiveness in the league and injuries across their career span. Our model is
designed to estimate the performance value of the player based on the attributes
and skill sets that the player possesses. Coaches can then take advantage of this
performance value and train the player, reshuffle the team, recruit, and loan or
sell the player. Another value added to this process is the market value of the
player obtained through the performance value of the player. However, there
will be an approximate deviation in that value by a certain amount due to
irregularities in the demand for a particular position, club budget, contract
period, injuries and current on-field performance.
1.1 PROBLEM DEFINITION
In the game of football (soccer), the evaluation of players for transfer, scouting,
squad formation and strategic planning is important. However, due to the vast
pool of grassroots level player, short career span, differing performance
throughout the individual’s career, differing play conditions, positions and
varying club budgets, it becomes difficult to identify the individual player's
performance value altogether. Our Player Performance Prediction system aims
at solving this complex problem analytically and involves learning from various
attributes and skills of a football player. The objective of this system is to help
the coaches and team management at the grassroots as well as higher levels to
identify the future prospects in the game of football without being biased to
subjective conditions like club budget, competitiveness in the league, and
importance of the player in the team or region.
Using machine learning algorithms predicting the results of a football match, we
obtained and create set of features, thus developing with high accurate
predictive method using machine learning techniques.

1.2. DECISION TREE

Decision Trees are a type of Supervised Machine Learning (that is you explain
what the input is and what the corresponding output is in the training data)
where the data is continuously split according to a certain parameter. The tree
can be explained by two entities, namely decision nodes and leaves. The leaves
are the decisions or the final outcomes. And the decision nodes are where the
data is split.

An example of a decision tree can be explained using above binary tree. Let’s
say you want to predict whether a person is fit given their information like age,
eating habit, and physical activity, etc. The decision nodes here are questions
like ‘What’s the age?’, ‘Does he exercise?’, ‘Does he eat a lot of pizzas’? And
the leaves, which are outcomes like either ‘fit’, or ‘unfit’. In this case this was a
binary classification problem (a yes no type problem).
There are two main types of Decision Trees:
Classification trees (Yes/No types)
What we’ve seen above is an example of classification tree, where the outcome
was a variable like ‘fit’ or ‘unfit’. Here the decision variable is Categorical.

Regression trees (Continuous data types)

Here the decision or the outcome variable is Continuous, e.g. a number like 123.
Working
Now that we know what a Decision Tree is, we’ll see how it works internally.
There are many algorithms out there which construct Decision Trees, but one of
the best is called as ID3 Algorithm. ID3 Stands for Iterative Dichotomiser 3.
Before discussing the ID3 algorithm, we’ll go through few definitions.

1.3.BOOST ALGORITHM
Boosting Algorithms combines each weak learner to create one strong
prediction rule. To identify the weak rule, there is a base Learning algorithm
(Machine Learning). Whenever the Base algorithm is applied, it creates new
prediction rules using the iteration process. After some iteration, it combines all
weak rules to create one single prediction rule.
To choose the right distribution follows the below-mentioned steps:
Step 1: The base Learning algorithm combines each distribution and applies
equal weight to each distribution.
Step 2: If any prediction occurs during the first base learning algorithm, then
we pay high attention to that prediction error.
Step 3: Repeat step 2 until the limit of the Base Learning algorithm has been
reached or high accuracy.
Step 4: Finally, it combines all the weak learner to create one strong prediction
rule.
 CHAPTER-2
LITERATURE SURVEY
Literature survey is the most important step in software development process.
Before developing the tool it is necessary to determine the time factor, economy
and company strength. Once these things are satisfied, then the next step is to
determine which operating system and language can be used for developing the
tool. Once the programmers start building the tool the programmers need lot of
external support. This support can be obtained from senior programmers, from
book or from websites. Before building the system the above consideration are
taken into account for developing the proposed system. The major part of the
project development sector considers and fully survey all the required needs for
developing the project. For every project Literature survey is the most important
sector in software development process. Before developing the tools and the
associated designing it is necessary to determine and survey the time factor,
resource requirement, man power, economy, and company strength. Once these
things are satisfied and fully surveyed, then the next step is to determine about
the software specifications in the respective system such as what type of
operating system the project would require, and what are all the necessary
software are needed to proceed with the next step such as developing the tools,
and the associated operations.

2.1.Predicting student performance using ID3 and C4.5 classification

algorithms
An educational institution needs to have an approximate prior knowledge of
enrolled students to predict their performance in future academics. This helps
them to identify promising students and also provides them an opportunity to
pay attention to and improve those who would probably get lower grades. As a
solution, we have developed a system which can predict the performance of
students from their previous performances using concepts of data mining
techniques under Classification. We have analyzed the data set containing
information about students, such as gender, marks scored in the board
examinations of classes X and XII, marks and rank in entrance examinations
and results in first year of the previous batch of students. By applying the ID3
(Iterative Dichotomiser 3) and C4.5 classification algorithms on this data, we
have predicted the general and individual performance of freshly admitted
students in future examinations.
2.2.Chess game result prediction system
In this project we train World Chess Federation (FIDE) rating systems using a
training dataset of a recent eleven-year period with games from 2000 chess
players. We will then use our system to predict the outcome of chess games
played by the same players in the following half year. Accuracy between
predicted results and actual game results is the primary indicator of whether our
approach is a practical chess rating system.

2.3.Predicting sports events from past results: Towards effective betting on

football matches
A system for predicting the results of football matches that beats the
bookmakers’ odds is presented. The predictions for the matches are based on
previous results of the teams involved.
2.4.Football result prediction with Bayesian Network in Spanish league
Barcelona team
The problem of modeling football data has become increasingly popular in the
last few years and many different models have been proposed with the aim of
estimating the characteristics that bring a team to lose or win a game, or to
predict the score of a particular match. We propose a Bayesian Network (BN) to
predict results of football matches. During the last decade, Bayesian networks
(and probabilistic graphical models in general) have become very popular in
artificial intelligence. In this paper, we look at the performance of a BN in the
area of predicting the result of football matches involving Barcelona FC. The
period under study was the 2008-2009 season in Spanish football league and we
test its performance. We get necessary information about football states from
valid websites. This BN is used for prediction of football results in future
matches.
 CHAPTER 3
SYSTEM REQUIREMENTS
3.1.HARDWARE REQUIREMENTS
System : Pentium i3 Processor
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 2 GB

3.2.SOFTWARE REQUIREMENTS
Operating system : Windows 10
Coding Language : Python
3.3. LANGUAGE SPECIFICATION
Python is a general-purpose interpreted, interactive, object-oriented, and high-
level programming language. It was created by Guido van Rossum during 1985-
1990. Like Perl, Python source code is also available under the GNU General
Public License (GPL). This tutorial gives enough understanding on Python
programming language.
3.4. HISTORY OF PYTHON
Python was developed by Guido van Rossum in the late eighties and early
nineties at the National Research Institute for Mathematics and Computer
Science in the Netherlands.

Python is derived from many other languages, including ABC, Modula-3, C,

C++, Algol-68, SmallTalk, and Unix shell and other scripting languages.