Machine Learning-Based Steam Platform Game's Popularity Analysis

Wenxiang Hu, Yiming Wang, Ruoming Xia

2024

Abstract

This study delves into the application of machine learning techniques to analyze game popularity on the Steam platform. Utilizing a diverse array of algorithms such as logistic regression, Support Vector Machine (SVM), decision tree, Gradient Boosting (XGBoost),Light Gradient Boosting Machine (LightGBM or LGBM), Deep Neural Networks (DNNs), and Convolutional Neural Networks (CNN), the research focuses on predicting game popularity through a thorough analysis of the Steam game dataset. The report meticulously outlines the stages of data preparation, including data cleaning and feature engineering, followed by the construction of various predictive models and their subsequent performance evaluation. Notably, the LGBM demonstrated a marked advantage, boasting an accuracy of 88.17% and an AUC of 80.36%. This investigation into game popularity on Steam not only aids game developers and companies in strategic planning and risk mitigation but also provides valuable insights for player community administrators to enhance community management. The comprehensive approach underscores the significant potential of machine learning in interpreting market trends and player preferences within the gaming industry.

Paper Citation

in Harvard Style

Hu W., Wang Y. and Xia R. (2024). Machine Learning-Based Steam Platform Game's Popularity Analysis. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 582-588. DOI: 10.5220/0012853800004547

in Bibtex Style

@conference{icdse24,
author={Wenxiang Hu and Yiming Wang and Ruoming Xia},
title={Machine Learning-Based Steam Platform Game's Popularity Analysis},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={582-588},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012853800004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Machine Learning-Based Steam Platform Game's Popularity Analysis
SN - 978-989-758-690-3
AU - Hu W.
AU - Wang Y.
AU - Xia R.
PY - 2024
SP - 582
EP - 588
DO - 10.5220/0012853800004547
PB - SciTePress