Design and Implementation of Insurance Product Recommendation System
DOI:
https://doi.org/10.54097/fcis.v1i2.1774Keywords:
Big Data Analysis, Insurance Product Recommendation, Hybrid recommendation algorithms, Spark FrameworkAbstract
In this paper, a hybrid collaborative filtering recommendation algorithm with Latent Dirichlet Allocation (LDA) and Alternating Least Squares (ALS) is proposed, which can effectively alleviate the cold start problem in traditional recommendation system and improve the accuracy of recommendation. At the same time, real-time recommendation according to the real-time behavior of users is realized in the real-time recommendation system, which effectively improves effectiveness of the recommendation results. In the system construction, user historical data is collected and analyzed by big data tools. Based on the Spark framework, the offline and real-time recommendation of insurance products are effectively combined and realized, with personalized recommendation as an important function. The designed system can improve the purchase rate and experience of users.
Downloads
References
Qazi M, Fung G M, Meissner K J, et al. An insurance recommendation system using Bayesian networks.Proceedings of the Eleventh ACM Conference on Recommender Systems[J]. Como, Italy. 2017. 274-278.
REINSEL D,GANTZ J,RYDNING J.The digitization of the world:from edge to core[J].IDC White Paper, ,2018,41(07):1619-1647.
Impact of data characteristics on recommender systems performance[J].Gediminas Adomavicius,Jingjing Zhang. ACM Transactions on Management Information Systems （TMIS）. 2012 (1):79-89
Zhang L, Liu X, Cao Y, et al. O-Recommend: An Optimized User-Based Collaborative Filtering Recommendation System[C]//2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS). IEEE, 2018: 212-219.
Chai Z Y, Li Y L, Han Y M, et al. Recommendation system based on singular value decomposition and multi-objective immune optimization[J]. IEEE Access, 2018, 7: 6060-6071.
Yang Q. A novel recommendation system based on semantics and context awareness[J]. Computing, 2018, 100(8): 809-823.
ÖZCAN İ, ÇELİK M. Developing Recommendation System Using Genetic Algorithm Based Alternative Least Squares [C]//2018 International Conference on Artificial Intelligence and Data Processing (IDAP). IEEE, 2018: 1-5.
Shaikh S, Rathi S, Janrao P. Recommendation system in E-commerce websites: A Graph Based Approached[C]//2017 IEEE 7th International Advance Computing Conference (IACC). IEEE, 2017: 931-934.
Nilashi M, Ibrahim O B, Ithnin N, et al. A multi-criteria collaborative filtering recommender system for the tourism domain using Expectation Maximization (EM) and PCA-ANFIS[J].Electronic Commerce Research & Applications, 2015.
Koren Y. Factorization meets the neighborhood: a multifaceted collaborative filtering model[C] //Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. 2020: 426-434.
Zhang S, Yao L, Xu X. AutoSVD++ An Efficient Hybrid Collaborative Filtering Model via Contractive Auto-encoders [C]//Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval. 2021: 957-960.
