Sistem Rekomendasi Produk Elektronik Berbasis Collaborative Filtering Manggunakan Matrix Factorization
Abstract
Sistem rekomendasi adalah suatu program yang
melakukan prediksi suatu item, dalam pembuatan sistem
rekomendasi terdapat Beberapa metode yang dapat digunakan
diantaranya Collaborative Filtering karena dianggap mampu
memberikan saran item yang lebih akurat. pendekatan
Collaborative Filtering karena dianggap mampu memberikan
saran item yang lebih akurat. Pada penelitian ini akan dibuat
sistem rekomendasi menggunakan 3 Algoritma Turunan MF
yaitu Singular Value Decomposition (SVD), SVD++, NonNegative Matrix Factorization NMF terhadap dataset Amazon
Review dengan Studi Kasus Elektronik, ini perlu diaplikasikan
dalam penelitian sistem rekomendasi, karena data Elektronik
ini mempunyai jumlah data yang sangat besar. Dalam
penelitian ini akan dilakukan uji coba terhadap beberapa
parameter yang meliputi n-epochs, n-factor dalam mekanisme
5-fold cross-validation. Untuk menangani data yang terlalu
besar, penulis melakukan random sampling sebesar 25% dari
total dataset untuk mengurangi beban komputasi. Dari hasil uji
coba didapatkan performansi rata-rata terbaik MAE = 1.0384
dan RMSE = 1.3139 yaitu pada Algoritma SVD.
Kata kunci— Produk Elektronik, Sistem Rekomendasi,
Collaborative Filtering, Matrix Factorization, Cross Validation
References
R. Mu, “A Survey of Recommender Systems Based
on Deep Learning,” IEEE Access, vol. 6, pp. 69009–
, 2018, doi: 10.1109/ACCESS.2018.2880197.
C. Channarong, C. Paosirikul, S. Maneeroj, and A.
Takasu, “HybridBERT4Rec: A Hybrid (ContentBased Filtering and Collaborative Filtering)
Recommender System Based on BERT,” IEEE
Access, vol. 10, pp. 56193–56206, 2022, doi:
1109/ACCESS.2022.3177610.
D. Jannach and M. Zanker, Value and Impact of
Recommender Systems. 2022. doi: 10.1007/978-1-
-2197-4_14.
P. Sharma and L. Yadav, “Movie Recommendation
System Using Item Based Collaborative Filtering,”
International Journal of Innovative Research in
Computer Science & Technology, vol. 8, no. 4, pp. 8–
, 2020, doi: 10.21276/ijircst.2020.8.4.2.
X. Guan, C. T. Li, and Y. Guan, “Matrix
Factorization with Rating Completion: An Enhanced
SVD Model for Collaborative Filtering
Recommender Systems,” IEEE Access, vol. 5, pp.
–27678, 2017, doi:
1109/ACCESS.2017.2772226.
I. Saifudin and T. Widiyaningtyas, “Systematic
Literature Review on Recommender System:
Approach, Problem, Evaluation Techniques,
Datasets,” IEEE Access, vol. 12, no. November 2023,
pp. 19827–19847, 2024, doi:
1109/ACCESS.2024.3359274.
D. Seng, G. Chen, and Q. Zhang, “Item-Based
Collaborative Memory Networks for
Recommendation,” IEEE Access, vol. 8, pp. 213027–
, 2020, doi:
1109/ACCESS.2020.3039380.
Y. Zhang, “An Introduction to Matrix factorization
and Factorization Machines in Recommendation
System, and Beyond,” pp. 1–15, 2022, [Online].
Available: http://arxiv.org/abs/2203.11026
Y. Koren, “Factorization meets the neighborhood,”
pp. 426–434, 2008, doi: 10.1145/1401890.1401944.
N. Hug, “Surprise: A Python library for
recommender systems,” J Open Source Softw, vol. 5,
no. 52, p. 2174, 2020, doi: 10.21105/joss.02174.
X. Luo, M. Zhou, Y. Xia, and Q. Zhu, “An efficient
non-negative matrix-factorization-based approach to
collaborative filtering for recommender systems,”
IEEE Trans Industr Inform, vol. 10, no. 2, pp. 1273–
, 2014, doi: 10.1109/TII.2014.2308433.
H. Hartatik, S. D. Nurhayati, and W. Widayani,
“Sistem Rekomendasi Wisata Kuliner di Yogyakarta
dengan Metode Item-Based Collaborative Filtering,”
Journal Automation Computer Information System,
vol. 1, no. 2, pp. 55–63, 2021, doi:
47134/jacis.v1i2.8.
