Skip to content
Permalink
main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

GW_PointsPredictor/ReadMe.md

Go to file
 
 
Cannot retrieve contributors at this time
1 lines (1 sloc) 1023 Bytes
Raw Blame
Open in GitHub Desktop
This project investigates the influences of luck and analysis on the outcome in Fantasy Premier League (FPL), a complex and interactive game with over 11.4 million users worldwide. Developing an algorithm to predict points scored in each game week by integrating a wide range of features/factors to assess against actual outcomes, the aim is to understand the impact of unpredictable elements like injuries, suspension etc in the game. With total players in each team being over 24 (20 teams in total) and only a half of them playing regularly, CatBoostClassifier was used to predict likelihood of starting players in each game week and LGBMRegressor to predict their expected points in that particular game week. To enhance the prediction accuracy, an array of features like historical data, position, value etc. were incorporated. By examining the intersection of analysis and luck in the game, this project aims to provide practical insights for FPL manager/users to optimize their team selection and improve gameplay.