Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69223
Volume:
10 |
11 |
Nov 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science
Nehru College of Management
Department of Computer Science
Nehru College of Management
Game development requires substantial investment under uncertain market demand. This paper presents the design of a pre-release decision-support system that estimates the popularity category of a proposed Steam game using features available before launch. The proposed Python and Streamlit application accepts genre, supported operating systems, languages, planned price, multiplayer support, and release year. A supervised classification pipeline predicts low, medium, or high popularity and reports model-derived probabilities. A separate retrieval and natural-language-processing module identifies historically similar games, summarizes Steam recommendation labels, and extracts recurring player feedback. To avoid target leakage, post-release reviews and ownership counts are excluded from predictive inputs, although they may define historical targets or support explanatory analysis. The manuscript specifies data integration, validation, model comparison, and evaluation methods. Quantitative results are intentionally not reported because model training and independent testing have not yet been verified.
KEYWORDS
This paper specifies a Steam game popularity prediction system that combines pre-release machine learning with separate historical review analysis. The design enables developers to enter planned game attributes, obtain a popularity classification, inspect comparable released games, and understand common player feedback. Its central methodological requirement is the strict separation of pre-release predictors from post-release outcome and review information. A reproducible implementation, representative historical data, calibrated probabilities, and honest evaluation are necessary before claims about predictive performance can be made.
[1] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001. [2] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011. [3] B. Liu, Sentiment Analysis and Opinion Mining. San Rafael, CA, USA: Morgan & Claypool, 2012. [4] Valve Corporation, “Steamworks Web API documentation.” [Online]. Available: https://partner.steamgames.com/doc/webapi [5] Streamlit, “Streamlit documentation.” [Online]. Available: https://docs.streamlit.io/ [6] Valve Corporation, “Steam Store.” [Online]. Available: https://store.steampowered.com/
Publication Date
11/20/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
0
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...