Football_Prediction_Project by Mhaythornthwaite - A Flask Template

Football_Prediction_Project

This project pulls past game data from api-football, and uses this to predict the outcome of future premier league matches with the use of classical machine learning techniques.

Overview:

This document discusses the process of building a model to predict the outcome of Premier League football matches using data collected from an API. The study aimed to achieve a test accuracy of over 50% with realistic output probabilities. The data cleaning and preparation, feature engineering, model training, and evaluation are detailed in the document.

Features:

Data Collection: Data collected directly from the api-football API for up-to-date information.
Feature Engineering: Utilizing average match data over the previous 10 games and generating difference metrics for key features.
Data Visualization: Visualizing feature differences like Goal Difference, Shot Difference, and more to analyze their impact on match outcomes.

Summary:

The document outlines the process of building a model to predict Premier League football match outcomes using API data. Features like feature engineering and data visualization were used to enhance model accuracy. The study aimed to achieve a test accuracy of over 50% with realistic output probabilities, showing promising results for predicting future matches accurately.