An Intelligent Recommendation System Utilizing a Hybrid Deep Learning Method
Received: 18 May 2025 | Revised: 9 June 2025 | Accepted: 21 June 2025 | Online: 15 July 2025
Corresponding author: Triyanna Widiyaningtyas
Abstract
Recommender systems play a crucial role in enhancing user experience by providing personalized product suggestions, attempting to increase sales and company profitability. However, current methodologies encounter two significant limitations: i) unidirectional models for review information extraction are unable to capture complex contextual semantics effectively, and ii) inefficiency when applied to large-scale datasets. The aim of this research is to develop a novel Hybrid Deep Learning and Probabilistic Matrix Factorization (HD-PMF) model to address the data sparsity problem in recommender systems. This research method is a combination of Bidirectional Long Short-Term Memory (BiLSTM) to capture contextual semantics from user reviews, Stacked Denoising Autoencoder (SDAE) to extract robust latent features from user data, and PMF optimized using Stochastic Gradient Descent (SGD) for accurate rating prediction. The results of this research are based on experiments conducted on two benchmark datasets with high sparsity levels: MovieLens 1M (95.35%) and Amazon Information Video (AIV) (99.98%). The HD-PMF model achieves a Root Mean Square Error (RMSE) of 0.4864, significantly outperforming baseline models such as PMF, Collaborative Deep Learning (CDL), LSTM-PMF, and Dual Deep Learning (DDL)-PMF. These results demonstrate that HD-PMF is an effective and promising approach for improving recommendation accuracy.
Keywords:
recommender system, hybrid deep learning, probabilistic matrix factorizationDownloads
References
L. De Divitiis, F. Becattini, C. Baecchi, and A. Del Bimbo, "Disentangling Features for Fashion Recommendation," ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 19, no. 1s, pp. 1–21, Feb. 2023. DOI: https://doi.org/10.1145/3531017
Z. Liu, W. Xu, W. Zhang, and Q. Jiang, "An emotion-based personalized music recommendation framework for emotion improvement," Information Processing & Management, vol. 60, no. 3, May 2023, Art. no. 103256. DOI: https://doi.org/10.1016/j.ipm.2022.103256
A. Panteli and B. Boutsinas, "Improvement of similarity–diversity trade-off in recommender systems based on a facility location model," Neural Computing and Applications, vol. 35, no. 1, pp. 177–189, Jan. 2023. DOI: https://doi.org/10.1007/s00521-020-05613-z
N. Chekkai and H. Kheddouci, "TOP-Key Influential Nodes for Opinion Leaders Identification in Travel Recommender Systems," in Advances in Model and Data Engineering in the Digitalization Era, vol. 1751, P. Fournier-Viger, A. Hassan, L. Bellatreche, A. Awad, A. Ait Wakrime, Y. Ouhammou, and I. Ait Sadoune, Eds. Cham: Springer Nature Switzerland, 2022, pp. 149–161.
X. Guo, L. Wang, M. Zhang, and G. Chen, "First Things First? Order Effects in Online Product Recommender Systems," ACM Transactions on Computer-Human Interaction, vol. 30, no. 1, pp. 1–35, Feb. 2023. DOI: https://doi.org/10.1145/3557886
S. Nair, K. Patil, H. Waghela, and S. Pansambal, "Outfit recommendation–using image processing," Journal of Algebraic Statistics, vol. 13, no. 2, pp. 1699–1706, 2022.
S. Airen and J. Agrawal, "Movie Recommender System Using Parameter Tuning of User and Movie Neighbourhood via Co-Clustering," Procedia Computer Science, vol. 218, pp. 1176–1183, 2023. DOI: https://doi.org/10.1016/j.procs.2023.01.096
Z. Z. Darban and M. H. Valipour, "GHRS: Graph-based hybrid recommendation system with application to movie recommendation," Expert Systems with Applications, vol. 200, Aug. 2022, Art. no. 116850. DOI: https://doi.org/10.1016/j.eswa.2022.116850
A. T. Khomeiny, T. Restu Kusuma, A. N. Handayani, A. Prasetya Wibawa, and A. H. Supadmi Irianti, "Grading System Recommendations for Students using Fuzzy Mamdani Logic," in 2020 4th International Conference on Vocational Education and Training (ICOVET), Malang, Indonesia, Sep. 2020, pp. 1–6. DOI: https://doi.org/10.1109/ICOVET50258.2020.9230299
Q. Zhao, X. Chen, H. Zhang, and X. Li, "Dynamic Hierarchical Attention Network for news recommendation," Expert Systems with Applications, vol. 255, Dec. 2024, Art. no. 124667. DOI: https://doi.org/10.1016/j.eswa.2024.124667
G. Behera and N. Nain, "DeepNNMF:deep nonlinear non-negative matrix factorization to address sparsity problem of collaborative recommender system," International Journal of Information Technology, vol. 14, no. 7, pp. 3637–3645, Dec. 2022. DOI: https://doi.org/10.1007/s41870-022-00982-1
T. Widiyaningtyas, D. D. Prasetya, and H. W. Herwanto, "Time Loss Function-based Collaborative Filtering in Movie Recommender System.," International Journal of Intelligent Engineering & Systems, vol. 16, no. 6, 2023. DOI: https://doi.org/10.22266/ijies2023.1231.84
S. Abinaya and K. U. Kumar, "Enhancing Multicriteria-Based Recommendations by Alleviating Scalability and Sparsity Issues Using Collaborative Denoising Autoencoder," Computers, Materials & Continua, vol. 78, no. 2, pp. 2269–2286, 2024. DOI: https://doi.org/10.32604/cmc.2024.047167
S. Gheewala, S. Xu, S. Yeom, and S. Maqsood, "Exploiting deep transformer models in textual review based recommender systems," Expert Systems with Applications, vol. 235, Jan. 2024, Art. no. 121120. DOI: https://doi.org/10.1016/j.eswa.2023.121120
L. Guo, L. Sun, R. Jiang, Y. Luo, and X. Zheng, "Recommendation based on attributes and social relationships," Expert Systems with Applications, vol. 234, Dec. 2023, Art. no. 121027. DOI: https://doi.org/10.1016/j.eswa.2023.121027
B. Kumar, N. Sharma, B. Sharma, N. Herencsar, and G. Srivastava, "Hybrid Recommendation Network Model with a Synthesis of Social Matrix Factorization and Link Probability Functions," Sensors, vol. 23, no. 5, Feb. 2023, Art. no. 2495. DOI: https://doi.org/10.3390/s23052495
R. Salakhutdinov and A. Mnih, "Probabilistic Matrix Factorization," in Proceedings of the 21st International Conference on Neural Information Processing Systems, Red Hook, NY, USA, 2007, pp. 1257–1264.
H. Wang, N. Wang, and D.-Y. Yeung, "Collaborative Deep Learning for Recommender Systems," in Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney NSW Australia, Aug. 2015, pp. 1235–1244. DOI: https://doi.org/10.1145/2783258.2783273
J. Liu, D. Wang, and Y. Ding, "PHD: A Probabilistic Model of Hybrid Deep Collaborative Filtering for Recommender Systems," in Proceedings of the Ninth Asian Conference on Machine Learning, Yonsei University, Seoul, Republic of Korea, Nov. 2017, vol. 77, pp. 224–239.
Hanafi and B. Mohd Aboobaider, "Word Sequential Using Deep LSTM and Matrix Factorization to Handle Rating Sparse Data for E‐Commerce Recommender System," Computational Intelligence and Neuroscience, vol. 2021, no. 1, Jan. 2021. DOI: https://doi.org/10.1155/2021/8751173
Hanafi et al., "Handling Sparse Rating Matrix for E-commerce Recommender System Using Hybrid Deep Learning Based on LSTM, SDAE and Latent Factor," International Journal of Intelligent Engineering and Systems, vol. 15, no. 2, pp. 379–393, Apr. 2022. DOI: https://doi.org/10.22266/ijies2022.0430.35
X. Guo and X. Cui, "A Cloud Model-Based Collaborative Filtering Approach for Sparse Data Recommendation Systems," in 2024 5th International Symposium on Computer Engineering and Intelligent Communications (ISCEIC), Wuhan, China, Nov. 2024, pp. 149–152. DOI: https://doi.org/10.1109/ISCEIC63613.2024.10810141
H. I. Alshbanat, H. Benhidour, and S. Kerrache, "A survey of latent factor models in recommender systems," Information Fusion, vol. 117, May 2025, Art. no. 102905. DOI: https://doi.org/10.1016/j.inffus.2024.102905
D. E. Cahyani, A. P. Wibawa, D. D. Prasetya, L. Gumilar, F. Akhbar, and E. R. Triyulinar, "Text-Based Emotion Detection using CNN-BiLSTM," in 2022 4th International Conference on Cybernetics and Intelligent System (ICORIS), Prapat, Indonesia, Oct. 2022, pp. 1–5. DOI: https://doi.org/10.1109/ICORIS56080.2022.10031370
A. Pranolo, Y. Mao, A. P. Wibawa, A. B. P. Utama, and F. A. Dwiyanto, "Robust LSTM With Tuned-PSO and Bifold-Attention Mechanism for Analyzing Multivariate Time-Series," IEEE Access, vol. 10, pp. 78423–78434, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3193643
P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P.-A. Manzagol, "Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion," Journal of Machine Learning Research, vol. 11, pp. 3371–3408, Dec. 2010.
S. Forouzandeh, K. Berahmand, and M. Rostami, "Presentation of a recommender system with ensemble learning and graph embedding: a case on MovieLens," Multimedia Tools and Applications, vol. 80, no. 5, pp. 7805–7832, Feb. 2021. DOI: https://doi.org/10.1007/s11042-020-09949-5
Amazon Product Reviews (2018). J. Ni. [Online]. Available: https://cseweb.ucsd.edu/~jmcauley/datasets/amazon_v2/.
N. Idrissi and A. Zellou, "A systematic literature review of sparsity issues in recommender systems," Social Network Analysis and Mining, vol. 10, no. 1, Dec. 2020. DOI: https://doi.org/10.1007/s13278-020-0626-2
T. Widiyaningtyas, I. Hidayah, and T. B. Adji, "User profile correlation-based similarity (UPCSim) algorithm in movie recommendation system," Journal of Big Data, vol. 8, no. 1, Dec. 2021. DOI: https://doi.org/10.1186/s40537-021-00425-x
Downloads
How to Cite
License
Copyright (c) 2025 Abu Tholib, Triyanna Widiyaningtyas, Didik Dwi Prasetya
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
