.png)
AMIKOM-RECSYS: Enhancing Movie Recommender System using Large Language Model (ChatGpt), Deep Learning and Probabilistic Matrix Factorization
Abstract
E-commerce has become one of the most widely used digital applications globally, enabling personalized product discovery and purchasing. To support these services, recommender systems are essential, offering item suggestions based on user preferences. Most recommender systems rely on machine learning algorithms to estimate user-item relevance scores, often utilizing product ratings. However, a persistent challenge in this domain is the issue of data sparsity, where only a small fraction of users provides explicit ratings, leading to reduced accuracy in recommendation results. In this study, we introduce a novel hybrid recommendation algorithm, named AMIKOM-RECSYS, designed to address the sparsity problem and enhance rating prediction. Our model integrates three main components included a Large Language Model (LLM) using ChatGPT, a Transformer-based encoder (BERT), and Probabilistic Matrix Factorization (PMF). The LLM generates descriptive information about movies based on specific prompts, which is then passed to BERT to encode the content into meaningful 2D vector representations. These enriched embeddings are subsequently utilized by the PMF algorithm to predict missing user-item ratings. We evaluate the proposed model on two benchmark datasets, ML-1M and ML-10M using Root Mean Squared Error (RMSE) as the evaluation metric. The AMIKOM-RECSYS model achieved RMSE values of 0.8681 on ML-1M and 0.7791 on ML-10M under a 50:50 data split, outperforming several baseline models including CNN-PMF, LSTM-PMF, and Attention-PMF. These results highlight the effectiveness of integrating LLM and Transformer-based contextual understanding into matrix factorization frameworks. In future work, we plan to extend this framework by incorporating other matrix factorization techniques such as Singular Value Decomposition (SVD) and integrating additional sources of user information, including social media activity, to further improve recommendation performance.
Keywords
Full Text:
PDFReferences
J. Munson, B. Cummins, and D. Zosso, “An introduction to collaborative filtering through the lens of the Netflix Prize,” Apr. 01, 2025, Springer Science and Business Media Deutschland GmbH. doi: 10.1007/s10115-024-02315-z.
E. G. Muñoz, J. Parraga-Alava, J. Meza, J. J. Proaño Morales, and S. Ventura, “Housing fuzzy recommender system: A systematic literature review,” Heliyon, vol. 10, no. 5, Mar. 2024, doi: 10.1016/j.heliyon.2024.e26444.
W. Zhang and Z. Wu, “E-commerce recommender system based on improved K-means commodity information management model,” Heliyon, vol. 10, no. 9, May 2024, doi: 10.1016/j.heliyon.2024.e29045.
J. Wang, L. Zhu, T. Dai, Q. Xu, and T. Gao, “Low-rank and sparse matrix factorization with prior relations for recommender systems,” Applied Intelligence, vol. 51, no. 6, pp. 3435–3449, 2021, doi: 10.1007/s10489-020-02023-5.
S. Ahmadian, K. Berahmand, M. Rostami, S. Forouzandeh, P. Moradi, and M. Jalili, “Recommender Systems based on Non-negative Matrix Factorization: A Survey,” IEEE Transactions on Artificial Intelligence, 2025.
Y. Koren, R. Bell, and C. Volinsky, “Matrix Factorization Techniques for Recommender Systems,” IEEE, vol. 40, no. 8, pp. 42–49, 2009.
F. Colace, D. Conte, M. De Santo, M. Lombardi, D. Santaniello, and C. Valentino, “A content-based recommendation approach based on singular value decomposition,” Conn Sci, vol. 34, no. 1, pp. 2158–2176, 2022, doi: 10.1080/09540091.2022.2106943.
J. Wu et al., “IT-PMF: A Novel Community E-Commerce Recommendation Method Based on Implicit Trust,” Mathematics, vol. 10, no. 14, Jul. 2022, doi: 10.3390/math10142406.
Y. Yan and C. Fu, “Transforming Movie Recommendations with Advanced Machine Learning: A Study of NMF, SVD, and K-Means Clustering.”
F. M. Harper and J. A. Konstan, “The MovieLens Datasets: History and Context,” ACM Trans. Interact. Intell. Syst., vol. 5, no. 4, pp. 19:1--19:19, 2015, doi: 10.1145/2827872.
I. Saifudin and T. Widiyaningtyas, “Systematic Literature Review on Recommender System: Approach, Problem, Evaluation Techniques, Datasets,” IEEE Access, vol. 12, pp. 19827–19847, 2024, doi: 10.1109/ACCESS.2024.3359274.
W. Pan, “A Survey of Transfer Learning for Collaborative Recommendation with Auxiliary Data,” Neurocomputing, vol. 177, pp. 447–453, 2016, doi: 10.1016/j.neucom.2015.11.059.
Y. Koren, “Collaborative filtering with temporal dynamics,” Commun ACM, vol. 53, no. 4, p. 89, 2010, doi: 10.1145/1721654.1721677.
Y. Hu, C. Volinsky, and Y. Koren, “Collaborative filtering for implicit feedback datasets,” Proceedings - IEEE International Conference on Data Mining, ICDM, no. December 2008, pp. 263–272, 2008, doi: 10.1109/ICDM.2008.22.
G. Dror, N. Koenigstein, and Y. Koren, “Yahoo! Music Recommendations: Modeling Music Ratings with Temporal Dynamics and Item Taxonomy,” Proceedings of the 5th ACM conference on Recommender systems - RecSys ’11, pp. 165–172, 2011, doi: 10.1145/2043932.2043964.
C. Wang and D. M. Blei, “Collaborative Topic Modeling for Recommending Scientific Articles,” Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD ’11, p. 448, 2011, doi: 10.1145/2020408.2020480.
H. Wang, N. Wang, and D.-Y. Yeung, “Collaborative Deep Learning for Recommender Systems,” in KDD conference, Sydney: ACM, 2015. doi: 10.1145/2783258.2783273.
P. G. Duran, A. Karatzoglou, J. Vitrià, X. Xin, and I. Arapakis, “Graph Convolutional Embeddings for Recommender Systems,” 2021, [Online]. Available: http://arxiv.org/abs/2103.03587
G. Ling, M. R. Lyu, and I. King, “Ratings meet reviews, a combined approach to recommend,” Proceedings of the 8th ACM Conference on Recommender systems - RecSys ’14, pp. 105–112, 2014, doi: 10.1145/2645710.2645728.
S. Ge and X. Ge, “An SVD-based Collaborative Filtering approach to alleviate cold-start problems,” Proceedings - 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2012, no. Fskd, pp. 1474–1477, 2012, doi: 10.1109/FSKD.2012.6233900.
R. M. Bell, Y. Koren, P. Ave, and F. Park, “Scalable Collaborative Filtering with Jointly Derived Neighborhood Interpolation Weights ∗,” in KDD Cup and Workshop, ACM, 2007.
H. Wang, N. Wang, and D.-Y. Yeung, “Collaborative Deep Learning for Recommender Systems,” in KDD conference, New South Wales: ACM, 2015, pp. 1235–1244. doi: 10.1145/2783258.2783273.
J. Wei, J. He, K. Chen, Y. Zhou, and Z. Tang, “Collaborative filtering and deep learning based recommendation system for cold start items,” Expert Syst Appl, vol. 69, pp. 1339–1351, 2017, doi: 10.1016/j.eswa.2016.09.040.
D. Kim, C. Park, J. Oh, S. Lee, and H. Yu, “Convolutional Matrix Factorization for Document Context-Aware Recommendation,” pp. 233–240, 2016, doi: 10.1145/2959100.2959165.
Hanafi, “Enhance Rating Prediction for E-commerce Recommender System Using Hybridization of SDAE, Attention Mechanism and Probabilistic Matrix Factorization,” International Journal of Intelligent Engineering and Systems, vol. 15, no. 5, pp. 427–438, 2022, doi: 10.22266/ijies2022.1031.37.
Hanafi and B. M. Aboobaider, “Word Sequential Using Deep LSTM and Matrix Factorization to Handle Rating Sparse Data for E-Commerce Recommender System,” Comput Intell Neurosci, vol. 2021, no. 1, 2021, doi: https://doi.org/10.1155/2021/8751173 Research.
Hanafi, N. Suryana, and A. S. H. Basari, “Dynamic convolutional neural network for eliminating item sparse data on recommender system,” International Journal of Advances in Intelligent Informatics, vol. 4, no. 3, 2018, doi: 10.26555/ijain.v4i3.291.
Hanafi, N. Suryana, and A. S. H. Basari, “Involve Convolutional-NN to Generate Item Latent Factor Consider Product Genre to Increase Robustness in Product Sparse Data for E-commerce Recommendation,” J Phys Conf Ser, vol. 1201, no. 1, 2019, doi: 10.1088/1742-6596/1201/1/012004.
Hanafi, N. Suryana, and A. S. B. H. Basari, “Convolutional-NN and word embedding for making an effective product recommendation based on enhanced contextual understanding of a product review,” Int J Adv Sci Eng Inf Technol, vol. 9, no. 3, pp. 1063–1070, 2019, doi: 10.18517/ijaseit.9.3.8843.
J. Liu and D. Wang, “PHD : A Probabilistic Model of Hybrid Deep Collaborative Filtering for Recommender Systems,” in ACML, 2017, pp. 224–239.
B. Zhang, H. Zhang, X. Sun, G. Feng, and C. He, “Integrating an attention mechanism and convolution collaborative filtering for document context-aware rating prediction,” IEEE Access, vol. 7, pp. 3826–3835, 2019, doi: 10.1109/ACCESS.2018.2887100.
Z. Zhang, Q. Wu, Y. Zhang, and L. Liu, “Movie recommendation model based on probabilistic matrix decomposition using hybrid AdaBoost integration,” PeerJ Comput Sci, vol. 9, pp. 1–19, 2023, doi: 10.7717/PEERJ-CS.1338.
C. Feng, J. Liang, P. Song, and Z. Wang, “A fusion collaborative filtering method for sparse data in recommender systems,” Inf Sci (N Y), vol. 521, pp. 365–379, 2020, doi: 10.1016/j.ins.2020.02.052.
A. Vaswani et al., “Attention is all you need,” Adv Neural Inf Process Syst, vol. 30, 2017.
R. Salakhutdinov and A. Mnih, “Probabilistic Matrix Factorization.,” Proc. Advances in Neural Information Processing Systems 20 (NIPS 07), pp. 1257–1264, 2007, doi: 10.1145/1390156.1390267.
D. Kim, C. Park, J. Oh, and H. Yu, “Deep hybrid recommender systems via exploiting document context and statistics of items,” Inf Sci (N Y), vol. 417, pp. 72–87, 2017, doi: 10.1016/j.ins.2017.06.026.
DOI: https://doi.org/10.47738/jads.v6i4.897
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0