This project involves scraping data from the MLS website, cleaning it, and using it to build a machine learning model that predicts player performance. The primary goal is to forecast the likelihood of a player scoring in an upcoming game.
The MLS website was selected as the primary data source due to its comprehensive and reliable repository of player career statistics.
- Data Scraping: Automated extraction of player data from the MLS website.
- Data Cleaning: Processing and refining the scraped data to ensure accuracy and usability.
- Machine Learning Model: Development and training of a predictive model to estimate the probability of a player scoring in future matches based on historical data.
This repository provides all the necessary scripts and instructions to replicate the data scraping, cleaning, and predictive modeling process. The end result is a robust tool that can aid in forecasting player performance in upcoming MLS games.