Predictive Analysis and Feature Importance of Successful Video Games

Team Details:

Team: KAP Team
Members:

Artem Guz
Kevin Dsouza
Peter Wong

Overview:

Framework: streamlit

Objective:
To analyze various video game datasets to determine the characteristics of successful games and develop a Machine Learning model that can predict the success of a video game based on its features, primarily focusing on Genre.

Datasets:

Popular Video Games
Video Games Data
Best Year for Video Games

Project Outline:

Depending on our final datasets, we will extract and compare the various variables, such as Genre, Developer, Release Date, and compare with variables commonly used to measure success for video games. This would be Total Sales, Region Sales, Ratings and more. Then, we will use this data to develop a model to determine if a game would be successful based on user input and idea.

Practical Application:

This project can provide valuable insights to game developers by highlighting the features and genres that are most likely to yield successful games, allowing them to make more informed decisions during the game development process.

1.0 Overall Concept:

1.0.1 Elevator Pitch:

To analyze various video game datasets to determine the characteristics of successful games and develop a Machine Learning model that can predict the success of a video game based on its features, primarily focusing on Genre.

1.0.2 Minimum Viable Product:

Details to be added

1.1 Group Members:

Since the group is just formed, we are still in the progress of finding position.

Group leader: Artem Guz

Members:

Artem Guz | College of Staten Island
- Primary role: Data collector and cleaner
- Secondary role: Model integration and testing
Kevin Dsouza | College of Staten Island
- Primary role: Data collector and cleaner
- Secondary role: Model integration and testing
Peter Wong | Brooklyn College
- Primary role: Data collector and cleaner
- Secondary role: Documentation and Documentation Review