Abstract
The widely-used field-aware factorization machines model (FFM) takes the interactions of all the text features into consideration which will lead to a large number of invalid calculations. An intelligent field-aware factorization machine model (iFFM) is proposed in this paper. In the model, the key attributes are promoted and the factor selection operations are embedded into the computation process intelligently by using the auto feature engineering technology. Meanwhile, Markov Chain Monte Carlo (MCMC) and stochastic gradient descent (SGD) methods are applied to optimize the loss function and improve the recommendation accuracy. In order to get better diversity, a new model iFFM-2 is put forward, which is the linear weighted combination of iFFM and a model built based on the heat-spreading algorithm. The experimental results show that iFFM can obtain higher accuracy and computation efficiency compared with FFMs, iFFM-2 inherits the accuracy of iFFM, and it can provide better diversity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
References
Xu, H., Zhang, R., Lin, C., Gan, W.: Construction of e-commerce recommendation system based on semantic annotation of ontology and user preference. Telkomnika Indonesian J. Electr. Eng. 12(3), 2028–2035 (2014)
Gupta, Y., Saini, A., Saxena, A.K., Gupta, Y., Saini, A., Saxena, A.K.: A new fuzzy logic based ranking function for efficient information retrieval system. Expert Syst. Appl. 42(3), 1223–1234 (2015)
Colombo-Mendoza, L.O., Valencia-García, R., Rodríguez-González, A., Alor-Hernández, G., Samper-Zapater, J.J.: RecomMetz: a context-aware knowledge-based mobile recommender system for movie showtimes. Expert Syst. Appl. 42(3), 1202–1222 (2015)
Gavalas, D., Kenteris, M.: A web-based pervasive recommendation system for mobile tourist guides. Pers. Ubiquit. Comput. 15(7), 759–770 (2011)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401(6755), 788–791 (1999)
Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Proceedings of SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 426–434. ACM, New York (2008)
Rendle, S., Schmidt-Thieme, L.: Pairwise interaction tensor factorization for personalized tag recommendation. In: Proceedings of SIGKDD International Conference on Web Search and Web Data Mining, pp. 81–90. ACM, New York (2010)
Rendle, S.: Factorization machines. In: ICDM, pp. 995–1000 (2010)
Rendle, S.: Factorization machines with libFM. ACM Transactions on Intelligent Systems & Technology 3(3), 219–224 (2012)
Platt, J.: A fast algorithm for training support vector machines. J. Inf. Technol. 2(5), 1–28 (1998)
Jahrer, M., Toscher, A., Lee, J.Y.: Ensemble of collaborative filtering and feature engineered models for click through rate prediction. In: Proceedings of KDD 2012, vol. 1, pp. 1–23. ACM, New York (2008)
Juan, Y., Zhuang, Y., Chin, W.S., Lin, C.J.: Field-aware factorization machines for CTR prediction. In: Proceedings of the 10th ACM Conference on Recommender Systems, pp. 43–50. ACM, New York (2016)
Zhou, T., Kuscsik, Z., Liu, J.G., Medo, M., Wakeling, J.R., Zhang, Y.C.: Solving the apparent diversity-accuracy dilemma of recommender systems. Proc. Nat. Acad. Sci. 107(10), 4511–4515 (2010)
Rendle, S.: Social network and click-through prediction with factorization machines. In: KDD Cup (2012)
Salakhutdinov, R., Mnih, A.: Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. In: Proceedings of International Conference on Machine Learning, pp. 880–887. ACM, New York (2008)
Zeiler, M.D.: Adadelta: An adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
Jahrer, M., Scher, A., Legenstein, R.: Combining predictions for accurate recommender systems. In: Proceedings of SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 693–702. ACM, New York (2010)
Sarwar, B., Karypis, G., Konstan, J., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th International Conference on World Wide Web, vol. 4, pp. 285–295. ACM, New York (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Yan, C., Zhang, Q., Zhao, X., Huang, Y. (2017). An Intelligent Field-Aware Factorization Machine Model. In: Candan, S., Chen, L., Pedersen, T., Chang, L., Hua, W. (eds) Database Systems for Advanced Applications. DASFAA 2017. Lecture Notes in Computer Science(), vol 10177. Springer, Cham. https://doi.org/10.1007/978-3-319-55753-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-55753-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-55752-6
Online ISBN: 978-3-319-55753-3
eBook Packages: Computer ScienceComputer Science (R0)