Can the data from EA's FIFA Potential Rating Help Bettors?

Posted on Mar 10, 2022

The skills the authors demonstrated here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

Preface

Anyone in sports betting or gambling all know that the odds are always against them, yet the enjoyment, chase, and optimism of winning make people continually bet even with or without any source of data to back up the odds. Finding a competitive advantage against the odds is always something that the community chases in order to make easier and better decisions.

In the world of soccer, one of the most exciting aspects of the game is the development of young players (players 23 and under). Watching their development creates excitement for the next generation of world class talents. The younger a player is, the more hype is created due to the amount of time that they can develop. Young players typically don't play at world class clubs due to playing time being limited and taken by already established standout players so they typically play at smaller clubs that allow them to gain the experience and development that will lead them to reach their potentials.

Most soccer players have their peak playing years in their late twenties so if a player is still a teenager with a few good performances in the first team, the media and fanbase tend to create a lot of optimism towards that player's potential especially if they play for a big club.

When the spotlight is on these youngsters, gamblers and bettors take notice and monitor these players. As a sports bettor, there are many aspects on soccer an individual can bet on like what stats could come out of a single game, player transfers throughout the season, coaching changes, or even the outcome of a team for the whole season. There's a lot of money to be won, but the algorithms and probabilities of how the odds are calculated are quite complex that bettors need to have extensive knowledge of the game, league, nation, etc. to make decisions that could win a lot of money or lose a lot of money.

Project Objective

In this project we will see if a bettor or gambler can use FIFA, a video game series developed by Electronic Arts(EA) , to see if their rating system data on youngsters can influence betting decisions or investments into memorabilia.

Our metric to use whether we can use FIFA as an influencer in betting or buying memorabilia is to see proportions of a youngster hitting their potential rating (what they are touted to be according to EA). I'd like to check if we can select a random youngster from the current iteration of FIFA and based on EA's  rating system, have another affirmation on whether to take on a bet. If there are good results from this study, we can potentially use  these findings to bet or invest on certain scenarios such as:

  • If a top rated youngster plays for an underdog team and is playing against a world class club
  • A youngster has rumors of transferring
  • Where a youngster's club can finish in the table
  • A youngster's or his teammate's stats for a specific game or for a season
  • Buying and selling sports cards/memorabilia
  • Etc.

Background Information and Data on FIFA

EA’s bestselling video game, FIFA, is enjoyed by millions around the world. With 350 million copies sold, people of all backgrounds come, play as their favorite team and players, and take on other gamers or the video game’s AI.  Each soccer player has a potential rating and overall rating. Potential rating is what their best overall rating will be in the future. The overall rating is what a player's rating is for a specific iteration of FIFA.

Player ratings in FIFA are developed by a lot of metrics from EA's development team. It's an aggregate of player's real life  ability and performances, media’s opinion on them, and many other factors. Ratings can range anywhere from 28-99.

Based on the standards of the best soccer clubs, world class players are generally rated 87+  by EA, with people being 92+ considered icons once in a generation type players and icons of the whole game. Players rated 84-86 are crucial first team players or first team players that are a notch below world class. If players are rated 83 or below, for world class soccer clubs, these players can range from crucial first team players  all the way to squad rotational players and youngsters.

Process and Visualizations of Data

To get the dataset to research FIFA, I first web scraped sofifa.com, a website dedicated to displaying all players potential rating for the future and their overall rating any iteration of FIFA. I scraped data from the top 300 potentially rated youngsters from FIFA 10 all the way to FIFA 21. Potential ratings range anywhere from 82-95.

Here is a sample of how my dataset would look after I web scraped sofifa.com

 

 

Afterwards I analyzed whether the youngsters hit their potential or not. I classified each player as someone who succeeded (either lived or exceeded their potential). In this case a person reached or exceeded their potential rating in either the FIFA that the potential rating was stated in or in a later FIFA. A player flopped when their overall ratings in any later FIFA did not reach their potential rating of a specific FIFA  and they at least hit their prime playing years.

If a player is classified as still young, they haven't hit their potential rating from any specific FIFA yet and to this day are still younger than their prime playing years. According to The Athletic, the average peak playing years for each player depends on their position and is as follows:

  • Goalkeepers: 27-29
  • Fullbacks: 24-26
  • Centerbacks: 26:28
  • Central Midfielders: 24-26
  • Central Attacking Midfielders: 25-27
  • Wide Midfielders and attackers: 25-27
  • Center Forwards/ Strikers: 26-28

 

These are examples of how I compared each players potential rating using data. I would compare the potential rating of a specific FIFA and then check all of their overall ratings for the next FIFA up until FIFA 22.

This is an example of a player who exceeded their potential rating from FIFA 10:

Note: The horizontal black line represents the potential rating from the FIFA being analyzed, in this case FIFA 10, and the blue line represents the overall ratings from each Fifa.

 

 

This is an example of a player who didn't live up to their expectations their potential rating from FIFA 10:

 

I analyzed the top 300 potential youngsters for each fifa and all FIFAs. Here's the player outcomes  for each FIFA.

 

data

 

Here's the breakdown for all 3600 players analyzed from all the FIFAs.

 

data

After analyzing the player outcomes of  each FIFA and all FIFAs, I then analyzed youngsters hitting their potential by age. The analysis can be shown right below

 

data

 

Conclusions so far from the data:

From analyzing the player outcomes in each iteration of FIFA, there was no FIFA where the proportion of players hitting or exceeded their potential was at least 50% . When we looked at all 3600 players, only 17% of players hit or exceeded their potential. There's still 27% of those players that are still youngsters so if we rule them out, out of all the players that hit their prime playing years, only 23% lived to or exceeded their potential.

When analyzing player outcomes by age, the proportion of players hitting their potential or exceeding them ranged anywhere from 12-22%. From the initial findings, it doesn't seem like a great idea to pick a random youngster and use EA's rating system as another affirmation to take on a bet or buying memorabilia.

An individual still needs extensive knowledge of the sport, knowledge of media opinions, knowledge of performances, and gut feeling when taking on bets or buying memorabilia.

Important notes about the data:

Just because a youngster doesn't reach a potential rating from a specific FIFA doesn't mean they lack quality in real life. Some of these youngsters may never had the overall rating of Messi or Ronaldo but that doesn't mean they can't compete against them.

I only analyzed the top 300 potential rated youngsters. There are thousands of youngsters in each FIFA but I only wanted to analyze the top 300 because the potential ratings start to become lower and thats when a player's potential start to become just average or below average. So this isn't a complete reflection on EA predicting a players potential, just on the top potential youngsters.

In the datasets, youngsters are repeated in a bunch of iterations of FIFA. For example, Virgil Van Dijk exceeded all his potential ratings when he was youngster. Then there are youngsters who never hit their potential rating in every FIFA or lived to their expectations in ever FIFA. Do these youngsters have an effect on the data and conclusions?

I used The Athletic's metric of prime playing years which is based on the distribution of minutes given to players based on age. That study was done for the premier league from the last 10 seasons.

If I had more time:

I would've analyzed player outcome by potential rating, club, position, and nation to see if EA had a better rating system based on these categories.

I would've also analyzed to see the youngsters' real life stats from past to see if there's a correlation between player potential ratings and real life stats.

About Author

Kenny Bagaloyos

Data Scientist with six years of experience in automotive and direct sales. Graduated with a BS in Business Management from Rutgers University in 2019.
View all posts by Kenny Bagaloyos >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories


Our Recent Popular Posts


View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI