Email this article 
(Department of Electrical Engineering, Applied Bachelor Program in Telecommunication Engineering, State Polytechnic of Sriwijaya, Indonesia)(2) * Ade Silvia Handayani
(Department of Electrical Engineering, Applied Bachelor Program in Telecommunication Engineering, State Polytechnic of Sriwijaya, Indonesia)(3) Suzanzefi Suzanzefi
(Department of Electrical Engineering, Applied Bachelor Program in Telecommunication Engineering, State Polytechnic of Sriwijaya, Indonesia)(4) Muhammad Zakuan Agung
(Department of Electrical Engineering, Applied Bachelor Program in Telecommunication Engineering, State Polytechnic of Sriwijaya)(5) Ella Rosita
(Palembang Training Center and Sriwijaya Coffee Community)(6) Asriyadi Asriyadi
(Electronics And Communication Engineering Department, King Abdul Aziz University, Jeddah)(7) Afifah Syifah Kaila
(Department of Electrical Engineering, Applied Bachelor Program in Telecommunication Engineering, State Polytechnic of Sriwijaya, Indonesia)(8) Luthfia Afifah
(Department of Electrical Engineering, Applied Bachelor Program in Telecommunication Engineering, State Polytechnic of Sriwijaya, Indonesia)(9) M. Ardiansyah
(Department of Electrical Engineering, Applied Bachelor Program in Telecommunication Engineering, State Polytechnic of Sriwijaya, Indonesia)*corresponding author
AbstractThis paper examines the use of a Restricted Boltzmann Machine (RBM) to provide personalized product recommendations on a niche coffee e-commerce platform facing cold-start conditions. We train RBM variants on a binary transaction matrix derived from 100 simulated user transactions and evaluate four hidden-unit configurations (3, 5, 10, 15) using 5-fold cross-validation. Models were trained with Contrastive Divergence (CD-1) and assessed primarily by Mean Squared Error (MSE) for reconstruction fidelity, complemented by ranking metrics (Precision@3, NDCG@3). The 10-hidden-unit configuration achieved the best balance of reconstruction and ranking performance, with an average test MSE ? 0.0454, outperforming popular-item (MSE: 0.0802) and random (MSE: 0.0760) baselines. While the RBM demonstrates strong capability in modeling latent user preferences under sparse data, ranking metrics expose limitations when predicting exact top-N items in extremely sparse cases. The study highlights practical implications for early-stage niche marketplaces and suggests integrating content signals or hybridization to further improve top-N recommendation quality. KeywordsCold-start; E-commerce; Recommendation System; Restricted Boltzmann Machine
|
DOIhttps://doi.org/10.29099/ijair.v9i1.1.1551 |
Article metrics10.29099/ijair.v9i1.1.1551 Abstract views : 206 | PDF views : 16 |
Cite |
Full Text Download
|
References
J. David, E. Chapo, and S. Gustavo, “Intelligent systems with applications artificial intelligence and recommender systems in e-commerce . trends and research agenda,” vol. 24, no. December 2023, 2024, doi: 10.1016/j.iswa.2024.200435.
A.-M. Urdea and C. P. Constantin, “Exploring the impact of customer experience on customer loyalty in e-commerce,” in Proceedings of the International Conference on Business Excellence, vol. 15, no. 1, pp. 672–682, 2021, doi: 10.2478/picbe-2021-0063.
N. Glisovic, D. Kragic, and M. Tegner, “Item cold start in e-commerce recommender systems: a survey,” IEEE Access, vol. PP, p. 1, 2025, doi: 10.1109/ACCESS.2025.3611026.
H. Ko, S. Lee, Y. Park, and A. Choi, “A survey of recommendation systems: recommendation models, techniques, and application fields,” Electronics, vol. 11, no. 1, 2022, doi: 10.3390/electronics11010141.
N. Hazrati and M. Elahi, “Addressing the new item problem in video recommender systems by incorporation of visual features with restricted boltzmann machines,” Expert Systems, vol. 38, no. 3, 2021, doi: 10.1111/exsy.12645.
S. Wang, L. Cao, Y. Wang, Q. Z. Sheng, M. A. Orgun, and D. Lian, “A survey on session-based recommender systems,” ACM Computing Surveys, vol. 54, no. 7, 2023, doi: 10.1145/3465401.
K. N. Mishra, A. Mishra, P. N. Barwal, and R. K. Lal, “Natural language processing and machine learning-based solution of cold start problem using collaborative filtering approach,” Electronics, vol. 13, no. 21, 2024, doi: 10.3390/electronics13214331.
R. Alabdulrahman, “Towards personalized recommendation systems: Domain-driven machine learning techniques and frameworks,” 2020, [Online]. Available: http://dx.doi.org/10.20381/ruor-25236.
Q. Xiaodong and L. A. N. Jiabao, “Research on improved rbm recommendation algorithm based on gibbs sampling,” Scalable Computing: Practice and Experience, vol. 26, pp. 1017–1034, 2025, doi: 10.12694/scpe.v26i3.4166.
M. Benleulmi, I. Gasmi, N. Azizi, and N. Dey, “Explainable AI and deep learning models for recommender systems: State of the art and challenges,” Journal of Universal Computer Science, vol. 31, no. 4, pp. 383–421, 2025, doi: 10.3897/jucs.122380.
I. Technology, “Beyond accuracy: Understanding and modeling the role of user conformity in recommender systems,” no. March, 2024.
A. Sharma, N. Patel, and R. Gupta, “Enhancing AI-powered recommendation engines using collaborative filtering and neural network-based algorithms,” pp. 1–23, 2023.
P. Li, S. Azman, M. Noah, and H. M. Sarim, “A survey on deep neural networks in collaborative filtering recommendation systems,” in 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2022, pp. 121-126.
M. Wang and A. P. J. Yu, “Advancing responsible recommendation systems: Enhancing accuracy, diversity, and fairness,” no. May, 2025.
R. J. Kuo and J. T. Chen, “An application of differential evolution algorithm-based restricted boltzmann machine to recommendation systems,” pp. 701–712, doi: 10.3966/160792642020052103008.
D. K. Behera, M. Das, S. Swetanisha, and P. K. Sethy, “Hybrid model for movie recommendation system using content K-nearest neighbors and restricted boltzmann machine,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 23, no. 1, pp. 445–452, 2021, doi: 10.11591/ijeecs.v23.i1.pp445-452.
B. Kim et al., “CUPID: A real-time session-based reciprocal recommendation system for a one-on-one social discovery platform,” in IEEE International Conference on Data Mining Workshops (ICDMW), pp. 704–713, 2024, doi: 10.1109/ICDMW65004.2024.00097.
G. S. Ananth, K. Raghuveer, and S. V. Kumar, “Preference weighted restricted boltzmann machines for cold start recommendations,” no. June, pp. 307–311, 2022.
T. Arifin et al., “Pemanfaatan algoritma restricted boltzmann machines (RBM) untuk prediksi dini kanker paru-paru,” Jurnal Teknoinfo, vol. 5, no. 2, pp. 138–146, 2023, [in Indonesian].
X. Cao, S. Chen, and Z. Li, “Research on e-commerce user behavior analysis based on big data collaborative recommendation algorithm,” vol. 5, pp. 30–37, 2021, doi: 10.23977/cpcs.2021.5100.
E. S. Eriana and D. A. Zein, “Artificial intelligence,” Angewandte Chemie International Edition, vol. 6, no. 11, p. 1, 2023.
D. C. Fatihah and I. S. Saidah, “Model promosi marketplace berbasis artificial intelligence (AI) di Indonesia,” JMBI UNSRAT (Jurnal Ilmiah Manajemen Bisnis dan Inovasi Universitas Sam Ratulangi), vol. 8, no. 3, pp. 806–817, 2021, doi: 10.35794/jmbi.v8i3.35908, [in Indonesian].
F. H. J. Gesellschaft, I. Science, A. L. Reitbauer, J. Dat, B. Dipl, and M. Melcher, “Recommendation systems in (near) real-time,” vol. D, 2023.
N. Idrissi and A. Zellou, “A systematic literature review of sparsity issues in recommender systems,” Social Network Analysis and Mining, vol. 10, no. 1, 2020, doi: 10.1007/s13278-020-0626-2.
L. Liang, Z. Wen, Y. Shi, H. Liu, and W. Li, “Design of product recommendation system based on restricted boltzmann machine,” vol. 6, no. 3, pp. 20–22, 2022.
S. Malhotra, “Recommendation system based on restricted boltzmann machine,” no. July, pp. 4000–4004, 2020.
L. W. Member, X. H. Member, and X. W. Member, “A survey on accuracy-oriented neural recommendation: From collaborative filtering to information-rich recommendation,” pp. 1–20, 2022.
S. Lee, “The use of restricted boltzmann machines for clustering collaborative filtering,” Journal of Autonomous Intelligence, vol. 6, no. 3, pp. 1–12, 2023, doi: 10.32629/jai.v6i3.723.
A. Ibrahim et al., “A recommendation system for electric vehicles users based on restricted boltzmann machine and WaterWheel plant algorithms,” IEEE Access, vol. 11, pp. 145111–145136, Nov. 2023, doi: 10.1109/ACCESS.2023.3345342.
S. Sridhar, D. Dhanasekaran, and G. C. P. Latha, “Content-based movie recommendation system using MBO with DBN,” Intelligent Automation & Soft Computing, vol. 35, no. 3, pp. 3241–3257, 2023, doi: 10.32604/iasc.2023.030361.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
________________________________________________________
The International Journal of Artificial Intelligence Research
Organized by: Prodi Teknik Informatika Fakultas Teknologi Bisnis dan Sains
Published by: Universitas Dharma Wacana
Jl. Kenanga No. 03 Mulyojati 16C Metro Barat Kota Metro Lampung
Email: jurnal.ijair@gmail.com
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International License.