The purpose of this project is to create a predictive model that is able to predict the winning team in a game of League of Legends based on the parameters available at 10 minutes in game. One potential use of the outcomes of this project can be to assess and improve betting algorithms used by video game betting websites.
- Inferential Statistics
- Machine Learning
- Data Visualization
- Predictive Modeling
- Python
- Pandas, Numpy, Matplotlib, Seaborn
- Sklearn
- Jupyter
This project was based on the recent exponential growth of Esports in media. Over the last decade, League of Legends has attracted over hundreds of millions of viewers across multiple platforms including forty four million concurrent viewers during the World Championship. With the increase of popularity, there has been a rise in betting on games. Being able to accurately predict the outcome of the game based on early game statistics might help betters make accurate picks and help websites develop a better betting platform. So based on this information, the goal of this project was to develop predictive models that would be able to predict the winning team accurately based on game statistics at ten minutes. The dataset is from Kaggle and can be found here. Since the outcome is binary, a few classification models will be tested to see which provides the optimal predictions.
- data exploration/descriptive statistics
- writeup/reporting
- Clone this repo (for help see this tutorial).
- Raw Data is being kept here within this repo.
- Data processing/transformation/analysis notebooks are being kept here
- Feel free to contact team leads with any questions or if you are interested in contributing!