Ruben van Gemeren

FPL Player Performance Model

Predict the performance of FPL players based on their historical data

Machine LearningFeature EngineeringPipeline

Challenge

Automating the creation and updating of a ML predictor model based on historical data for predicting the performance of FPL players.

Approach

Creating a pipeline that creates features from historical data and trains a regression model using PyTorch, which is updated every week to predict the next week's performance of FPL players.

Impact

Create a webpage that displays the predicted performance of FPL players, with a live update every week. Based on real game data, the model can be updated to predict the performance of FPL players more accurately.

Tech Stack

PythonPyTorchHopsworks