Abstract
With the rapid development of personalized recommendation technology for big data, online data resources have undergone a rapid expansion, presenting features such as complex structure and diverse forms. For the purpose of improving recommendation accuracy, we adopt the idea of divide and conquer to construct a novel hybrid temporal prediction model to adapt to the features of different user interest data fluctuations. Firstly, the users’ data is divided into small and large ranges through fluctuation thresholds. Meanwhile, we introduce a global dynamic factor to adjust the temporal weight decay of the sequence data, and then use the neural network to regress and predict the small range fluctuation series data, at the same time, the large range fluctuation series data is predicted by dividing the fuzzy relationship through the membership degree of fuzzy clustering. Finally, through simulation recommendation experiments, model ablation experiments, and iterative performance experiments by using 8 baseline models and 7 datasets, the results show that the F1 index of the proposed model has increased by an average of 13.21%, the NDCG index has increased by an average of 15.96%, and the convergence iterations are within 600 times. More accurate prediction results can be received through extraction of data feature for different interest fluctuations, which is helpful for optimizing personalized information recommendation services.
Similar content being viewed by others
Data Availability
We used public datasets with the URL: http://deepyeti.ucsd.edu/jianmo/amazon/index.html.
References
Askari S, Montazerin N (2015) A high-order multi-variable fuzzy time series forecasting algorithm based on fuzzy clustering. Expert Syst Appl 42(4):2121–2135
Bargiela A, Pedrycz W (2003) Recursive information granulation: aggregation and interpretation issues. IEEE Trans Syst Man Cybern Part B (Cybernetics) 33(1):96–112
Binbusayyis A (2022) Deep embedded fuzzy clustering model for collaborative filtering recommender system. Intell Autom Soft Comput 33(1)
Bose M, Mali K (2018) A novel data partitioning and rule selection technique for modeling high-order fuzzy time series. Appl Soft Comput 63:87–96
Cheng C-H, Chen T-L, Teoh HJ, Chiang C-H (2008) Fuzzy time-series based on adaptive expectation model for taiex forecasting. Expert Syst Appl 34(2):1126–1132
Chen J, Lu Y, Shang F, Wang Y (2021) A fuzzy matrix factor recommendation method with forgetting function and user features. Appl Soft Comput 100:106910
Choi S-M, Ko S-K, Han Y-S (2012) A movie recommendation algorithm based on genre correlations. Expert Syst Appl 39(9):8079–8085
Deng Z-H, Huang L, Wang C-D, Lai J-H, Yu PS (2019) Deepcf: A unified framework of representation learning and matching function learning in recommender system. Proc AAAI Conf Artif Intell 33(1):61–68
Egrioglu E, Aladag CH, Yolcu U, Basaran MA, Uslu VR (2009) A new hybrid approach based on sarima and partial high order bivariate fuzzy time series forecasting model. Expert Syst Appl 36(4):7424–7434
Egrioglu E, Aladag CH, Yolcu U (2013) Fuzzy time series forecasting with a novel hybrid approach combining fuzzy c-means and neural networks. Expert Syst Appl 40(3):854–857
Hamidzadeh J, Rezaeenik E, Moradi M (2021) Predicting users¡¯ preferences by fuzzy rough set quarter-sphere support vector machine. Appl Soft Comput 112:107740
Hasija H, Chaurasia D (2015) Recommender system with web usage mining based on fuzzy c means and neural networks. In 2015 1st International Conference on Next Generation Computing Technologies (NGCT), pp 768–772. IEEE
Ismail Z, Efendi R (2011) Enrollment forecasting based on modified weight fuzzy time series. J Artif Intell 4(1):110–118
Kermany NR, Alizadeh SH (2017) A hybrid multi-criteria recommender system using ontology and neuro-fuzzy techniques. Electron Commer Res Appl 21:50–64
Levonian Z, Erikson DR, Luo W, Narayanan S, Rubya S, Vachher P, Terveen L, Yarosh S (2020) Bridging qualitative and quantitative methods for user modeling: Tracing cancer patient behavior in an online health community. Proc Int AAAI Conf Web Soc Media 14:405–416
Liu Y-T, Lin Y-Y, Shang-Lin Wu, Chuang C-H, Lin C-T (2015) Brain dynamics in predicting driving fatigue using a recurrent self-evolving fuzzy neural network. IEEE Trans Neural Netw Learn Syst 27(2):347–360
Logesh R, Subramaniyaswamy V, Malathi D, Sivaramakrishnan N, Vijayakumar V (2020) Enhancing recommendation stability of collaborative filtering recommender system through bio-inspired clustering ensemble method. Neural Comput Appl 32(7):2141–2164
Ni J, Li J, McAuley J (2019) Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 188–197
Ni J, Huang Z, Yang Hu, Lin C (2022) A two-stage embedding model for recommendation with multimodal auxiliary information. Inf Sci 582:22–37
Paradarami TK, Bastian ND, Wightman JL (2017) A hybrid recommender system using artificial neural networks. Expert Syst Appl 83:300–313
Pedrycz W, Vukovich G (2001) Abstraction and specialization of information granules. IEEE Trans Syst Man Cybern B (Cybernetics) 31(1):106–111
Pulido M, Melin P, Castillo O (2014) Particle swarm optimization of ensemble neural networks with fuzzy aggregation for time series prediction of the mexican stock exchange. Inf Sci 280:188–204
Saraswat M, Chakraverty S, Kala A (2020) Analyzing emotion based movie recommender system using fuzzy emotion features. Int J Inf Technol 12(2):467–472
Selvi C, Sivasankar E (2019) A novel optimization algorithm for recommender system using modified fuzzy c-means clustering approach. Soft Comput 23(6):1901–1916
Shang F, Liu Y, Cheng J, Yan Da (2017) Fuzzy double trace norm minimization for recommendation systems. IEEE Trans Fuzzy Syst 26(4):2039–2049
Shang H, Lu D, Zhou Q (2021) Early warning of enterprise finance risk of big data mining in internet of things based on fuzzy association rules. Neural Comput Appl 33(9):3901–3909
Shojaei M, Saneifar H (2021) Mfsr: A novel multi-level fuzzy similarity measure for recommender systems. Expert Syst Appl 177:114969
Vo T (2022) An integrated network embedding with reinforcement learning for explainable recommendation. Soft Comput 26(8):3757–3775
Wang G, Jia Q-S, Qiao J, Bi J, Liu C (2020) A sparse deep belief network with efficient fuzzy learning framework. Neural Netw 121:430–440
Yang H-F, Phoebe Chen Y-P (2019) Hybrid deep learning and empirical mode decomposition model for time series applications. Expert Syst Appl 120:128–138
Yilmaz S, Oysal Y (2010) Fuzzy wavelet neural network models for prediction and identification of dynamical systems. IEEE Trans Neural Networks 21(10):1599–1609
Yin H, Wong SC, Xu J, Wong CK (2002) Urban traffic flow prediction using a fuzzy-neural approach. Transp Res C Emerg Technol 10(2):85–98
Yuan X, Liebelt MJ, Shi P, Phillips BJ (2021) Creating rule-based agents for artificial general intelligence using association rules mining. Int J Mach Learn Cybern 12(1):223–230
Zadeh LA (1979) Fuzzy sets and information granularity. Adv Fuzzy Set Theory Appl 11:3–18
Funding
This work is supported by the Major Program of the National Social Science Foundation of China "Research on the accurate construction of urban and rural community service system driven by big data" (Grant No. 20&ZD154) and Postgraduate Research & Practice Innovation Program of Jiangsu Province "Research on Topic Mining and Knowledge Graph Construction for Time Series Commentary of Online Health Information."(Grant No. KYCX23_0079).
Author information
Authors and Affiliations
Contributions
Hao Ding: Conceptualization of this study, Methodology, Software.
Corresponding author
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ding, H. TNFRM: A recommendation model based on temporal interest fluctuation with neural networks and fuzzy clustering. Appl Intell 53, 25042–25057 (2023). https://doi.org/10.1007/s10489-023-04776-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04776-1