Abstract: This research presents a cross-domain evaluation framework for collaborative filtering in e-commerce, movies, and books, integrating data preprocessing, synthetic interaction modelling, feature engineering, and multi-metric evaluation. The framework integrates regression and classification metrics and allows for threshold recommendation modelling to enhance performance. The results indicate that Neural Collaborative Filtering always exhibits..
Index Terms – Collaborative Filtering; Matrix Factorization, Neural Collaborative Filtering (NCF); E-Commerce Recommendation; Machine Learning; Data Sparsity
[1].
Ibrahim, O. A. S., Younis, E. M. G., Mohamed, E. A., & Ismail, W. N., (2025). Revisiting Recommender Systems: An Investigative Survey. Neural Computing And Applications, 37(4), 2145–2173. Doi:10.1007/S00521-024-10828-5
[2].
Andika, H. G., Hadinata, M. T., Huang, W., Anderies, & Iswanto, I. A., (2022). Systematic Literature Review: Comparison On Collaborative Filtering Algorithms For Recommendation Systems. In Proceedings Of The IEEE International Conference On Communication, Networks And Satellite (COMNETSAT), 3–4 November (Pp. 56–61). Solo, Indonesia.
Doi:10.1109/COMNETSAT56033.2022.9994316
[3].
Wu, X., (2024). Review Of Collaborative Filtering Recommendation Systems. Advances In Computer Engineering, 43(1), 76–82. Doi:10.54254/2755-2721/43/20230811
[4].
Martins, G. B., Papa, J. P., & Adeli, H., (2020). Deep Learning Techniques For Recommender Systems Based On Collaborative Filtering. Expert Systems, 37(6), E12647. Doi:10.1111/Exsy.12647
[5].
Li, D., (2024). On The Theoretical Foundation Of Model Comparison And Evaluation For Recommender Systems. Arxiv Preprint. Doi:10.48550/Arxiv.2411.01843.
