Skip to content

rodrigogsvaz/projeto_predicao_brasileirao

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Logo do projeto

Prediction of game results in Brazilian Football Championship

🔥 Introdução

In this project, a simple deep learning model is trainned, optimized, and used to predict the whether a team will win a match playing in its own stadium.

Results show a acuracy of 56.34% compared to a natural class distribution of roughly 50%.

📦 Tecnologias usadas:

Coloque aqui as ferramentas que você usou para criar seu projeto, exemplo:

  • Python
  • Pandas
  • NumPy
  • scikit-learn
  • TensorFlow
  • Keras

📋 Next Steps

The project implementation is still very simple. Next steps will enrich the project.

  • Test more ANN architectures and other type of models
  • Get more data to make models more powerful
  • Train models to also predict multiclass target: win, withdraw, and lose
  • If you want to contribuite or have any suggestions, reach me out on linkedin =)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published