Collaborative Filtering Based Hybrid Recommendation System Using Neural Network and Matrix Factorization Techniques
Keywords:
Collaborative based filtering, Content based filtering, Coverage, Matrix factorization, Neural networks, Hybrid Recommendation systemAbstract
This research paper presents a novel work on collaborative filtering based hybrid recommendation system. A hybrid recommendation system is a best combination of content based filtering and collaborative based filtering recommendation systems. In recent years, recommendation systems have become an essential part of our daily lives, assisting us in making informed decisions about what to buy, read, watch, and listen to. Collaborative filtering (CF) and matrix factorization (MF) are widely used techniques for building recommendation systems. However, they suffer from certain constraints, such as the cold-start problem, sparsity, and scalability. Hybrid recommendation systems combine multiple recommendation algorithms to overcome individual algorithms' limitations and improve recommendations' accuracy and coverage. In our next contribution, we have suggested a hybrid recommendation system to enhance the accuracy and coverage of suggestions by combining MF with NN. On the other hand, deep learning-based approaches such as neural networks (NN) have shown great promise in overcoming these limitations. In this research, we propose a novel hybrid recommendation system that combines the strengths of MF and NN to improve the accuracy and diversity of recommendations. We evaluate the proposed method on three popular datasets MovieLense, Hind Movie and Book Crossing and compare its performance with other state-of-the-art recommendation algorithms. The results demonstrate that the proposed hybrid approach outperforms the individual MF and NN models and achieves better coverage with the lowest Root Mean Squared Error (RMSE).
Downloads
References
Koren, Y. (2008). Factorization meets the neighborhood: a multifaceted collaborative filtering model. Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, 426-434.
Liang, Y., Li, X., Sun, H., & Li, Z. (2016). Factorization meets association rule mining: A hybrid recommendation algorithm. Information Sciences, 345, 89-104.
Ji, S., Xu, W., Yang, M., & Yu, K. (2010). 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, 35(1), 221-231.
Mohammadiha, N., Nadernejad, E., & Esteki, A. (2013). Speech feature extraction using matrix factorization. International Journal of Signal Processing, Image Processing and Pattern Recognition, 6(2), 179-188.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26, 3111-3119.
He, X., Liao, L., Zhang, H., Nie, L., Hu, X., & Chua, T. S. (2017). Neural collaborative filtering. Proceedings of the 26th International Conference on World Wide Web, 173-182.
Zhang, S., Yao, L., & Sun, A. (2018). Deep learning based recommender system: A survey and new perspectives. ACM Computing Surveys (CSUR), 51(3), 42.
Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27, 3104-3112.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Image net classification with deep convolution neural networks. Advances in neural information processing systems, 25, 1097-1105.
H. A. C. Okan Sakar (2021). A Dynamic Recurrent Neural Networks-Based Recommendation System for Banking Customers, Signal Processing and Communications Applications Conference (SIU), Istanbul, pp. 1-4.
Zhang Q, Li Y, Zhang G, Lu J. A recurrent neural network-based recommender system framework and prototype for sequential E-learning. In Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference (FLINS 2020) 2020 (pp. 488-495).
Liang, Y., Li, X., Sun, H., & Li, Z. (2016). Factorization meets association rule mining: A hybrid recommendation algorithm. Information Sciences, 345, 89-104.
Li, C., Zheng, X., Zhang, W., Ma, J., & Yao, L. (2015). A hybrid recommendation system based on matrix factorization and neural networks. Journal of Computational Information Systems, 11(6), 1961-1968.
Wang, J., Zhang, Y., Liu, Y., & Yan, S. (2006). Learning to rank for personalized recommendations. Proceedings of the 15th international conference on World Wide Web, 761-769.
Zhang, L., Zheng, H., Li, Y., & Li, J. (2017). Deep learning based recommender system: A survey and new perspectives. ACM Computing Surveys (CSUR), 50(5), 1-35.
M. N. Tentua and Suprapto, “Recommendation system using machine learning: A review paper,” Int. J. Innov. Creat. Chang., vol. 12, no. 11, 2020.
K.K. Yadav, H. K. Soni, and N. Pathik, “Recommendation System Based on Double Ensemble Models using KNN-MF,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 5, 2023, doi: 10.14569/IJACSA.2023.0140566.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.