Predicting Steam Games Rating with Regression
Andreas Sukardi Teja, Muhammad Lukman I. Hanafi, Nunung Nurul Qomariyah
Last modified: 2022-06-08
Recommender system has been used in many industries to boost up their sales. One of the industries that feel the benefits of the emergence of recommender system is the game industry. This paper try to find out the best regression model to predict rating of a video games. It is done by comparing multiple variable related to Metascore, such as genres and player count. In order to be able get accurate result, we gather some data by scraping them from Steam and combine them with public data. The games in this study are from Steam since it is one of the largest computer video games distributors. In this study, we evaluate several regression models, such as Linear regression, Decision Tree, Random Forest to predict game rating. The experiment shows that tree based regression model, such as LightGBM and Random Forest performed better than any other regression method, with $R^2$ score above 0.9.
Game Rating Prediction, Steam Top Games, Game Meta-Score, Regression Models.
An account with this site is required in order to view papers. Click here
to create an account.