On identifying relevant features for a successful indie video game release on steam
Loading...
Journal Title
Journal ISSN
Volume Title
School of Business |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Author
Date
2024
Department
Major/Subject
Mcode
Degree programme
Information and Service Management (ISM)
Language
en
Pages
76
Series
Abstract
PC video game marketplace Steam has been the leading platform for customers to acquire new software after its launch in 2003. As a multi-sided platform, Steam provides different services besides selling games and has grown its popularity in the market. The emphasis of the thesis is on examining indie games and the reasons behind launch-time popularity measured in player averages. Publicly available data is gathered from first-party and third-party sources to be analysed with K-means clustering algorithm and Random Forest Regressor. Data is visualized in lower dimensions with the help of Principal Component Analysis. Relevant features consisting mostly of umbrella categories and Steam platform-specific functionalities were found. Findings of the relevant features are inspected in a critical light. The clustering of monthly player averages had promising results - implication for three clusters is present: unpopular games, popular games and very popular games. The clustering results proved useful in evaluating the soundness of the Random Forest Regressor feature importance results.Description
Thesis advisor
Viitasaari, LauriKeywords
steam, valve, indie games, video game publishing
