Feature Extracted Deep Neural Collaborative Filtering for E-Book Service Recommendations
Source abstract
Abstract
The electronic publication market is growing along with the electronic commerce market. Electronic publishing companies use recommendation systems to increase sales to recommend various services to consumers. However, due to data sparsity, the recommendation systems have low accuracy. Also, previous deep neural collaborative filtering models utilize various variables of datasets such as user information, author information, and book information, and these models have the disadvantage of requiring significant computing resources and training time for their training. To address this issue, we propose a deep neural collaborative filtering model with feature extraction that uses minimal data such as user number, book number, and rating information. The proposed model comprises an input layer for inputting and embedding the product and user data, a feature extraction layer for extracting the features through data correlation analysis between the embedded user and product data, a multilayer perceptron, and an output layer. To improve the performance of the proposed model, Bayesian optimization was used to determine hyperparameters. To evaluate the deep neural collaborative filtering model with feature extraction, a comparative analysis experiment was conducted with currently used collaborative filtering models. The goodbooks-10k public dataset was used, and the results of the experiment show that the low accuracy caused by data sparsity was considerably improved.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Recommender Systems and Techniques · Human Mobility and Location-Based Analysis · Digital Marketing and Social Media
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Contents AI Research Center, Romantique, 27 Daeyeong-ro, Busan 49227, Republic of Korea
Department of Distribution and Logistics, Tongmyong University, Busan 48520, Republic of Korea
Funding
Ministry of Education and National Research Foundation of Korea
References (49)
Show source-provided references
1. (2023, January 05). Internet Usage Statistics. Available online: https://www.internetworldstats.com/stats.htm.
2. The importance of e-books in improving students’ skills in physics learning in the 21st century: A literature review10.1088/1742-6596/2309/1/012061 ↗
3. Toward trustworthy recommender systems: An analysis of attack models and algorithm robustness
4. An inner-enterprise knowledge recommender system10.1016/j.eswa.2009.06.057 ↗
5. Guy, I., and Carmel, D. (April, January 28). Social recommender systems. Proceedings of the WWW ‘11: 20th International World Wide Web Conference, Hyderabad, India.
6. Improving scalability of personalized recommendation systems for enterprise knowledge workers10.1109/ACCESS.2015.2513000 ↗
7. Ricci, F., Rokach, L., and Shapira, B. (2015). Recommender Systems: Introduction and Challenge, Springer.10.1007/978-1-4899-7637-6 ↗
8. Sarwar, B., Karypis, G., Konstan, J., and Reidl, J. (2001, January 1–5). Item-based collaborative filtering recommendation algorithms. Proceedings of the 10th International Conference on World Wide Web (WWW), Hong Kong, China.10.1145/371920.372071 ↗
9. Zhao, A.D., and Shang, M.S. (2010, January 9–10). User-based collaborative-filtering recommendation algorithms on Hadoop. Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, Phuket, Thailand.
10. Hu, R., and Pu, P. (2011, January 23–27). Enhancing collaborative filtering systems with personality information. Proceedings of the RecSys ‘11: Fifth ACM Conference on Recommender Systems, Chicago, IL, USA.10.1145/2043932.2043969 ↗
11. A survey of active learning in collaborative recommender systems10.1016/j.cosrev.2016.05.002 ↗
12. A survey on deep learning for big data10.1016/j.inffus.2017.10.006 ↗
13. Barkan, O., and Koenigstein, N. (2016, January 13–16). ITEM2VEC: Neural item embedding for collaborative filtering. Proceedings of the 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing, Vietri sul Mare, Italy.10.1109/MLSP.2016.7738886 ↗
14. Zheng, L. (2023, January 06). A Survey and Critique of Deep Learning on Recommender Systems. Available online: https://bdsc.lab.uic.edu/docs/survey-critique-deep.pdf.
15. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., and Chua, T.S. (2017). Neural collaborative filtering. arXiv.10.1145/3038912.3052569 ↗
16. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., and Chua, T.S. (2018, January 9–19). Outer product-based neural collaborative filtering. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), Stockholm, Sweden.10.24963/ijcai.2018/308 ↗
17. Kim, D., Park, C., Oh, J., Lee, S., and Yu, H. (2016, January 15–19). Convolutional matrix factorization for document context-aware recommendation. Proceedings of the 10th ACM Conference, Boston, MA, USA.10.1145/2959100.2959165 ↗
18. Cheng, H.T. (2016). Wide & deep learning for recommender systems. arXiv.10.1145/2988450.2988454 ↗
19. Xiong, R., Wang, J., Li, Z., Li, B., and Hung, P.C.K. (2018, January 2–7). Personalized LSTM based matrix factorization for online QoS prediction. Proceedings of the 2018 IEEE International Conference on Web Services (ICWS), San Francisco, CA, USA.10.1109/ICWS.2018.00012 ↗
20. Taud, H., and Mas, J. (2018). Geomatic Approaches for Modeling Land Change Scenarios, Lecture Notes in Geoinformation and Cartography, Springer.
21. Deep hybrid collaborative filtering for Web service recommendation10.1016/j.eswa.2018.05.039 ↗
22. Image-based service recommendation system: A JPEG-coefficient RFs approach10.1109/ACCESS.2019.2962315 ↗
23. Dual-embedding based deep latent factor models for recommendation10.1145/3447395 ↗
24. A recommendation strategy integrating higher-order feature interactions with knowledge graphs10.1109/ACCESS.2022.3220322 ↗
25. Explainable recommendation via personalized features on dynamic preference interactions10.1109/ACCESS.2022.3219076 ↗
26. Fusing user reviews into heterogeneous information network recommendation model10.1109/ACCESS.2022.3176727 ↗
27. Neural collaborative autoencoder for recommendation with co-occurrence embedding10.1109/ACCESS.2021.3133628 ↗
28. Research on BP neural network recommendation model fusing user reviews and ratings10.1109/ACCESS.2021.3080079 ↗
29. Neural explicit factor model based on item features for recommendation systems10.1109/ACCESS.2021.3072539 ↗
30. He, K., Zhang, X., Ren, S., and Sun, j. (2015). Deep residual learning for image recognition. arXiv.10.1109/CVPR.2016.90 ↗
31. Ha, S., and Choi, S. (2016, January 24–29). Convolutional neural networks for human activity recognition using multiple accelerometer and gyroscope sensors. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.10.1109/IJCNN.2016.7727224 ↗
32. Kasagi, A., Tabaru, T., and Tamura, H. (2017, January 25–28). Fast algorithm using summed area tables with unified layer performing convolution and average pooling. Proceedings of the IEEE Workshop on Machine Learning for Signal Processing, Tokyo, Japan.10.1109/MLSP.2017.8168154 ↗
33. Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on International Conference on Machine Learning, Lille, France.
34. Agarap, A.F. (2018). Deep learning using rectified linear units. arXiv.
35. Klambauer, G., Unterthiner, T., Mayr, A., and Hochreiter, S. (2018, January 3–8). Self-normalizing neural networks. Proceedings of the Self-Normalizing Neural Networks, NIPS’17: 31st International Conference on Neural Information Processing Systems, Montreal, ON, Canada.
36. Clevert, D.A., Unterthiner, T., and Hochreiter, S. (2016, January 2–4). Fast and accurate, deep network learning by exponential linear units (ELUs). Proceedings of the ICLR 2016, San Juan, Puerto Rico.
37. Jastrzebski, S., Arpit, D., Ballas, N., Verma, V., Che, T., and Bentio, Y. (2018, January 16). Residual connections encourage iterative inference. Proceedings of the ICLR 2018 Conference, Vancouver, ON, Canada.
38. Exploring tunable hyperparameters for deep neural networks with industrial ADME data sets
39. Frazier, P.I. (2018). A tutorial on Bayesian optimization. arXiv.10.1287/educ.2018.0188 ↗
40. Turning hyperparameters of a SVM-based water demand forecasting system through parallel global optimization10.1016/j.cor.2018.01.013 ↗
41. Gradient based hyperparameter optimization in Echo State Networks10.1016/j.neunet.2019.02.001 ↗
42. Taking the human out of the loop: A review of Bayesian optimization10.1109/JPROC.2015.2494218 ↗
43. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference for Learning Representations, San Diego, CA, USA.
44. (2023, January 05). Goodbooks-10k. Available online: https://github.com/zygmuntz/goodbooks-10k.
45. Ghosh, S., Nahar, N., Wahab, M.A., and Biswas, M. (2021). Intelligent Computing and Optimization, Advances in Intelligent Systems and Computing, Springer.
46. Author, M.G., and Margaritis, K.G. (2005, January 8–10). Applying SVD on generalized item-based filtering. Proceedings of the 5th International Conference on Intelligent Systems Design and Applications (ISDA’05).
47. Howard, J., and Gugger, S. (2020). Fastai: A layered API for deep learning. Information, 11.10.3390/info11020108 ↗
48. Aggarwal, C.C. (2016). Recommender Systems: The Textbook, Springer.10.1007/978-3-319-29659-3 ↗
49. Meng, Z., McCreadie, R., Macdonald, C., and Ounis, I. (2020, January 22–26). Exploring data splitting strategies for the evaluation of recommendation models. Proceedings of the RecSys ’20: 14th ACM Conference on Recommender Systems, New York, NY, USA.10.1145/3383313.3418479 ↗