Perancangan Sistem Rekomendasi Game Steam dengan Neural Multi-Criteria Collaborative Filtering
Keywords:
Sistem rekomendasi, collaborative filtering, multi-criteria, neural network, game recommendation, cold startAbstract
Industri game digital telah mengalami pertumbuhan pesat dengan platform Steam Store menyediakan lebih dari 50.000 game, menciptakan masalah information overload bagi pengguna. Penelitian ini merancang sistem rekomendasi game Steam menggunakan pendekatan Neural Multi-Criteria Collaborative Filtering (MCCF) yang memprediksi empat kriteria rating (gameplay, graphics, value, overall) secara simultan. Sistem dilengkapi dengan cold start handler berbasis few-shot learning yang berjalan otomatis di backend tanpa menampilkan proses perhitungan ke pengguna. Dataset yang digunakan terdiri dari 21 game Steam dengan 21 atribut lengkap dan 500 profil pengguna hasil filtering yang menghasilkan 10.500 multi-criteria rating. Hasil perancangan menunjukkan sistem mampu menghasilkan rekomendasi game yang sesuai dengan preferensi pengguna, dengan contoh rekomendasi top-3 yaitu Elden Ring (prediksi overall 4,82), Hades (prediksi overall 4,71), dan The Witcher 3 (prediksi overall 4,65) untuk pengguna dengan preferensi genre RPG/Action dan graphics yang baik. Rancangan antarmuka sistem terdiri dari empat halaman dengan navigasi tab-based yang user-friendly. Hasil perancangan menunjukkan arsitektur model yang mampu menangkap preferensi multi-dimensi pengguna dengan representasi vektor 59-dimensi melalui deep matrix factorization dan task-specific heads.
References
[1] R. Blue, L. Garcia, and J. Turner, "SMU Data Science Review Game Recommendation Analysis Using Steam Profiles and Reviews," vol. 8, no. 1, 2024.
[2] Y. H. Alfaifi, "Recommender Systems Applications: Data Sources, Features, and Challenges," 2024.
[3] S. Gheewala, "In-depth survey: deep learning in recommender systems — exploring prediction and ranking models, datasets, feature analysis, and emerging trends," Neural Computing and Applications, vol. 37, no. 17, pp. 10875-10947, Springer London, 2025.
[4] T. Widiyaningtyas, I. Saifudin, I. Ari, E. Zaeni, M. Zulfiqar, and N. Maulana, "Memory-based collaborative filtering based on matrix factorization and Gower's set rank," Journal of King Saud University Computer and Information Sciences, vol. 37, no. 9, Springer International Publishing, 2025.
[5] M. Liu, M. Wang, B. Li, and Q. Zhong, "Collaborative filtering based on GNN with attribute fusion and broad attention," pp. 1-24, 2025.
[6] H. Hendersen, W. Susanto, R. Fredyan, H. H. Kurniawan, and M. Amien, "Movie Recommendation System: A Comparison of Content-Based and Collaborative Filtering," Procedia Computer Science, vol. 245, pp. 860-868, Elsevier B.V., 2024.
[7] E. Salkanovic and D. Kečo, "A Data Analysis of Steam's Game Catalog and Diverse Recommendation Strategies," vol. 186, no. 54, pp. 39-49, 2024.
[8] Y. Wang, "Research on Game Recommendation Algorithms Based on Hybrid Models," The 3rd International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE 2024), pp. 267-274, Association for Computing Machinery, 2024.
[9] H. L. Mulyana and F. Rumaisa, "Course Learning Recommendation System Using Neural Collaborative Filtering," vol. 4, no. 2, pp. 517-524, 2024.
[10] S. Wang, Y. Xu, S. Li, and J. Li, "Optimization of Weighted Hybrid Algorithm based on Collaborative Filtering and Content Filtering in Steam Game Recommendation," vol. 17, no. 2, 2025.
[11] A. P. Kumar, B. P. Kamath, and R. Shetty, "Product recommendation framework with enhanced item-based collaborative filtering," 2026.
[12] S. Raza et al., "A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice," 2024.
[13] W. E. Lomanto, A. A. Suryani, and T. Herlambang, "Collaborative Filtering for Steam Games Recommendation," in Proc. International Conference on Operational Research (ICOR 2023), 2023, pp. 30-35.
[14] A. Jadulhaq and Z. K. A. Baizal, "Games Recommender System Using Singular Value Decomposition," in 2023 3rd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA), Dec. 2023, pp. 1-6.
[15] S. Saaidin, "A Multicriteria and Hybrid Approach for Video Games Recommender," PhD Thesis, Universiti Teknologi MARA (UiTM), 2023.
