A Heterogeneous Information Network based Cross Domain Insurance Recommendation System for Cold Start Users

Liqiang Song
Liqiang Song
Mengqiu Yao
Mengqiu Yao
Zhenyu Wu
Zhenyu Wu
Jianming Wang
Jianming Wang

SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval Virtual Event China July, 2020, pp. 2211-2220, 2020.

Cited by: 0|Bibtex|Views62|DOI:https://doi.org/10.1145/3397271.3401426
EI
Other Links: dl.acm.org|dblp.uni-trier.de|arxiv.org|academic.microsoft.com
Weibo:
To deal with insurance product complexity and cold start problem, we propose a novel framework called a HCDIR for cold start users in insurance domain

Abstract:

Internet is changing the world, adapting to the trend of internet sales will bring revenue to traditional insurance companies. Online insurance is still in its early stages of development, where cold start problem (prospective customer) is one of the greatest challenges. In traditional e-commerce field, several cross-domain recommendation...More

Code:

Data:

0
Introduction
  • Internet is changing the world, every segment of the economy is experiencing dramatic change and is having to respond to shifts in the value chain, enhanced consumer power, and altered competitive cycles.
  • PingAn Jinguanjia, one of the most popular comprehensive applications (App) in China, which boasts more than 100 million registered users, has nearly 90% cold start users in insurance domain.
  • This situation resulted from many reasons.
  • Attracting prospective customers plays a critical role in buildup of the competitive edge for traditional insurance company.
  • These methods treat insurance domain and traditional e-commerce neglecting product complexity and data sparsity problem in insurance domain
Highlights
  • Internet is changing the world, every segment of the economy is experiencing dramatic change and is having to respond to shifts in the value chain, enhanced consumer power, and altered competitive cycles
  • PingAn Jinguanjia, one of the most popular comprehensive applications (App) in China, which boasts more than 100 million registered users, has nearly 90% cold start users in insurance domain
  • Given the complexity of insurance products and the data sparsity problem, we construct an insurance heterogeneous information network (IHIN) based on data from Jinguanjia App, the IHIN connects users, agents, insurance products and insurance product properties together, giving us richer underlying information
  • To deal with insurance product complexity and cold start problem, we propose a novel framework called a HCDIR for cold start users in insurance domain
  • We construct an IHIN based on data from Jinguanjia App, we employ three-level attention aggregations to get user and insurance product representations
Methods
  • Owing to separate training in three tasks in cold start scenario, single type of meta-paths cannot significantly affect the model performance while incorporation of all kinds of meta-paths can boost the performance.
  • For the hyper-parameters of the Adam optimizer,the authors set the learning rate α= 0.001.
  • These settings are chosen with grid search on the validation set.
  • The authors test the model performance on the validation set for every epoch.
Results
  • As shown in Table 6, the proposed HCDIR can at least improve by 76 %.
Conclusion
  • CONCLUSION AND FUTURE WORK

    To deal with insurance product complexity and cold start problem, the authors propose a novel framework called a HCDIR for cold start users in insurance domain.
  • The authors first try to learn more effective user and item latent features in both source and target domains.
  • The authors construct an IHIN based on data from Jinguanjia App, the authors employ three-level attention aggregations to get user and insurance product representations.
  • The authors will try to construct more complete HIN, considering more types of relations, such as the relation between agent and insurance product.
  • The authors will consider to train more accurate item representations in source domain
Summary
  • Introduction:

    Internet is changing the world, every segment of the economy is experiencing dramatic change and is having to respond to shifts in the value chain, enhanced consumer power, and altered competitive cycles.
  • PingAn Jinguanjia, one of the most popular comprehensive applications (App) in China, which boasts more than 100 million registered users, has nearly 90% cold start users in insurance domain.
  • This situation resulted from many reasons.
  • Attracting prospective customers plays a critical role in buildup of the competitive edge for traditional insurance company.
  • These methods treat insurance domain and traditional e-commerce neglecting product complexity and data sparsity problem in insurance domain
  • Objectives:

    Given rating matrices and HIN, the goal is to learn more effective latent features for users and items, and learn the mapping function from nonfinancial domain to insurance domain, which can help them deal with cold start users.
  • Methods:

    Owing to separate training in three tasks in cold start scenario, single type of meta-paths cannot significantly affect the model performance while incorporation of all kinds of meta-paths can boost the performance.
  • For the hyper-parameters of the Adam optimizer,the authors set the learning rate α= 0.001.
  • These settings are chosen with grid search on the validation set.
  • The authors test the model performance on the validation set for every epoch.
  • Results:

    As shown in Table 6, the proposed HCDIR can at least improve by 76 %.
  • Conclusion:

    CONCLUSION AND FUTURE WORK

    To deal with insurance product complexity and cold start problem, the authors propose a novel framework called a HCDIR for cold start users in insurance domain.
  • The authors first try to learn more effective user and item latent features in both source and target domains.
  • The authors construct an IHIN based on data from Jinguanjia App, the authors employ three-level attention aggregations to get user and insurance product representations.
  • The authors will try to construct more complete HIN, considering more types of relations, such as the relation between agent and insurance product.
  • The authors will consider to train more accurate item representations in source domain
Tables
  • Table1: Statistics of Our dataset
  • Table2: Ask-buy-ratio of different agents
  • Table3: Notations and descriptions
  • Table4: Performance comparison
  • Table5: Performance of variants of HCDIR on Jinguanjia dataset at 10% sparsity level inguanjia dataset at 10% sparsity level
  • Table6: Online performance of compared methods. âĂŸG_BaselineâĂŹ indicates the baseline performance of cold start user group using traditional method LightGBM; and âĂŸG_HCDIR without agentâĂŹ and âĂŸG_HCDIRâĂŹdenotes HCDIR without agent heterogeneous relationships and HCDIR, respectively
Download tables as Excel
Related work
  • 6.1 Insurance Recommendation System

    To our knowledge, there are not many papers about recommendation systems in insurance products domain, some includes [6, 14, 19, 20, 22]. [22] throughly describes the differences between recommendation system for classical domain and insurance domain, and focuses on call centers servicing Life and Annual insurance, where the agents also have limited knowledge and experience. [6] propose a web recommendation system for life insurance sector by using association rules, which is one of the most well researched techniques of data mining. [19] presents a hybird recommendation system in insurance domain based on a standard user-user collaborate filtering approach. [20] utilizes Bayes networks to give customers personalized recommendation based on what other similar people with similar portfolios have. [11] is a improved model of [20], which tries to learn the structure of Bayesian network and considerably speeds up both training and inference run-times, while achieving similar accuracy. [14] propose a causation-driven visualization system that fundamentally transforms cross-media insurance data into network diagrams and performs recommendation reasoning. However, these methods neglect the item complexity and data sparsity problem.

    6.2 Cross-domain Recommendation

    Cross-domain recommendation (CDR) [5, 12, 13, 16, 17, 28], which aims to improve the recommendation performance by means of transferring information from the auxiliary domain to the target domain, is one of the promising ways to solve data sparsity and cold start problem. Generally, CDR can be categorized into two categories. One is to aggregate knowledge between two domains, this kind of methods are interested in improving the overall performance in the target domain [13, 16, 28], however, they can not deal with cold start users. Since cold start users do not have any interactions in target domain. The other one aims at infering the preferences of cold start users based on their preferences observed in other domains [5, 12, 17]. These methods assume that there exists overlap in information between users and/or items across different domains, and train a mapping function from the source-domain into the target-domain. For cold start users, these method first learn representations in source domain, and then mapping them to the target domain.
Reference
  • Behnoush Abdollahi and Olfa Nasraoui. 2016. Explainable Matrix Factorization for Collaborative Filtering. In Proceedings of the 25th International Conference on World Wide Web, WWW 2016, Montreal, Canada, April 11-15, 2016, Companion Volume. 5–6. https://doi.org/10.1145/2872518.2889405
    Locate open access versionFindings
  • Junyoung Chung, Çaglar Gülçehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. CoRR abs/1412.3555 (2014). arXiv:1412.3555 http://arxiv.org/abs/1412.3555
    Findings
  • Yuxiao Dong, Nitesh V. Chawla, and Ananthram Swami. 2017. metapath2vec: Scalable Representation Learning for Heterogeneous Networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada, August 13 - 17, 2017. 135–144. https://doi.org/10.1145/3097983.3098036
    Locate open access versionFindings
  • Tao-Yang Fu, Wang-Chien Lee, and Zhen Lei. 2017. HIN2Vec: Explore Metapaths in Heterogeneous Information Networks for Representation Learning. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore, November 06 - 10, 2017. 1797–1806. https://doi.org/10.1145/3132847.3132953
    Locate open access versionFindings
  • Wenjing Fu, Zhaohui Peng, Senzhang Wang, Yang Xu, and Jin Li. 2019. Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019. 94–101. https://doi.org/10.1609/aaai.v33i01.330194
    Locate open access versionFindings
  • Abdhesh Gupta and Anwiti Jain. 2013. Life insurance recommender system based on association rule mining and dual clustering method for solving cold-start problem. International Journal of Advanced Research in Computer Science and Software Engineering 3 (Oct. 2013).
    Google ScholarLocate open access versionFindings
  • William L. Hamilton, Zhitao Ying, and Jure Leskovec. 201Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA. 1024–1034.
    Google ScholarLocate open access versionFindings
  • Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2016. Session-based Recommendations with Recurrent Neural Networks. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings. http://arxiv.org/abs/1511.06939
    Findings
  • Binbin Hu, Chuan Shi, Wayne Xin Zhao, and Philip S. Yu. 2018. Leveraging Metapath based Context for Top- N Recommendation with A Neural Co-Attention Model. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018, London, UK, August 19-23, 2018. 1531– 1540. https://doi.org/10.1145/3219819.3219965
    Locate open access versionFindings
  • Binbin Hu, Zhiqiang Zhang, Chuan Shi, Jun Zhou, Xiaolong Li, and Yuan Qi. 2019. Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, Honolulu, Hawaii, USA, January 27 February 1, 2019. 946–953. https://doi.org/10.1609/aaai.v33i01.3301946
    Locate open access versionFindings
  • Teja Kanchinadam, Maleeha Qazi, Joseph Bockhorst, Mary Y. Morell, Katie J. Meissner, and Glenn Fung. 2018. Using Discriminative Graphical Models for Insurance Recommender Systems. In 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, Orlando, FL, USA, December 17-20, 2018. 421–428. https://doi.org/10.1109/ICMLA.2018.00069
    Locate open access versionFindings
  • SeongKu Kang, Junyoung Hwang, Dongha Lee, and Hwanjo Yu. 2019. SemiSupervised Learning for Cross-Domain Recommendation to Cold-Start Users. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, November 3-7, 2019. 1563– 1572. https://doi.org/10.1145/3357384.3357914
    Locate open access versionFindings
  • Tzu-Heng Lin, Chen Gao, and Yong Li. 2019. CROSS: Cross-platform Recommendation for Social E-Commerce. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, Paris, France, July 21-25, 2019. 515–524. https://doi.org/10.1145/3331184.
    Locate open access versionFindings
  • Zhixiu Liu, Chengxi Zang, Kun Kuang, Hao Zou, Hu Zheng, and Peng Cui.
    Google ScholarFindings
  • 2019. Causation-Driven Visualizations for Insurance Recommendation. In IEEE International Conference on Multimedia & Expo Workshops, ICME Workshops 2019, Shanghai, China, July 8-12, 2019. 471–476. https://doi.org/10.1109/ICMEW.2019.00087
    Locate open access versionFindings
  • [15] Yuanfu Lu, Chuan Shi, Linmei Hu, and Zhiyuan Liu. 2019. Relation StructureAware Heterogeneous Information Network Embedding. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019. 4456–4463. https://doi.org/10.1609/aaai.v33i01.33014456
    Locate open access versionFindings
  • [16] Muyang Ma, Pengjie Ren, Yujie Lin, Zhumin Chen, Jun Ma, and Maarten de Rijke. 2019. π -Net: A Parallel Information-sharing Network for Shared-account Crossdomain Sequential Recommendations. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, Paris, France, July 21-25, 2019. 685–694. https://doi.org/10.1145/3331184.3331200
    Locate open access versionFindings
  • [17] Tong Man, Huawei Shen, Xiaolong Jin, and Xueqi Cheng. 2017. Cross-Domain Recommendation: An Embedding and Mapping Approach. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19-25, 2017. 2464–2470. https://doi.org/10.24963/ijcai.2017/343
    Locate open access versionFindings
  • [18] Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. 3111–31http://papers.nips.cc/paper/5021-distributedrepresentations-of-words-and-phrases-and-their-compositionality
    Locate open access versionFindings
  • [19] Sanghamitra Mitra, Nilendra Chaudhari, and Bipin Patwardhan. 2014. Leveraging hybrid recommendation system in insurance domain. International Journal of Engineering and Computer Science 3 (Oct. 2014).
    Google ScholarLocate open access versionFindings
  • [20] Maleeha Qazi, Glenn M. Fung, Katie J. Meissner, and Eduardo R. Fontes. 2017. An Insurance Recommendation System Using Bayesian Networks. In Proceedings of the Eleventh ACM Conference on Recommender Systems, RecSys 2017, Como, Italy, August 27-31, 2017. 274–278. https://doi.org/10.1145/3109859.3109907
    Locate open access versionFindings
  • [21] Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2012. BPR: Bayesian Personalized Ranking from Implicit Feedback. CoRR abs/1205.2618 (2012). arXiv:1205.2618 http://arxiv.org/abs/1205.2618
    Findings
  • [22] Lior Rokach, Guy Shani, Bracha Shapira, Eyal Chapnik, and Gali Siboni. 2013. Recommending insurance riders. In Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC ’13, Coimbra, Portugal, March 18-22, 2013. 253–260. https://doi.org/10.1145/2480362.2480417
    Locate open access versionFindings
  • [23] F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini. 2009. The Graph Neural Network Model. IEEE Transactions on Neural Networks 20, 1 (2009), 61–80. https://doi.org/10.1109/TNN.2008.2005605
    Locate open access versionFindings
  • [24] Michael Sejr Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling Relational Data with Graph Convolutional Networks. In The Semantic Web - 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3-7, 2018, Proceedings. 593–607. https://doi.org/10.1007/978-3-319-93417-4_38
    Locate open access versionFindings
  • [25] Yizhou Sun, Jiawei Han, Xifeng Yan, Philip S. Yu, and Tianyi Wu. 2011. PathSim: Meta Path-Based Top-K Similarity Search in Heterogeneous Information Networks. PVLDB 4, 11 (2011), 992–1003.
    Google ScholarLocate open access versionFindings
  • [26] Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In Proceesings of the 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018. https://openreview.net/forum?id=rJXMpikCZ Minjie Wang, Lingfan Yu, Da Zheng, Quan Gan, Yu Gai, Zihao Ye, Mufei Li, Jinjing Zhou, Qi Huang, Chao Ma, Ziyue Huang, Qipeng Guo, Hao Zhang, Haibin Lin, Junbo Zhao, Jinyang Li, Alexander J Smola, and Zheng Zhang.2019. Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs. ICLR Workshop on Representation Learning on Graphs and Manifolds (2019).https://arxiv.org/abs/1909.01315
    Findings
  • Xiang Wang, Xiangnan He, Liqiang Nie, and Tat-Seng Chua. 2017. Item Silk Road: Recommending Items from Information Domains to Social Users. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Tokyo, Japan, August 7-11, 2017. 185–194. https://doi.org/10.1145/3077136.3080771
    Locate open access versionFindings
  • Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Yanfang Ye, Peng Cui, and Philip S. Yu. 2019. Heterogeneous Graph Attention Network. In The World Wide Web Conference, WWW 2019, San Francisco, CA, USA, May 13-17, 2019. 2022–2032. https://doi.org/10.1145/3308558.3313562
    Locate open access versionFindings
  • Fengli Xu, Jianxun Lian, Zhenyu Han, Yong Li, Yujian Xu, and Xing Xie. 2019. Relation-Aware Graph Convolutional Networks for Agent-Initiated Social ECommerce Recommendation. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, November 3-7, 2019. 529–538. https://doi.org/10.1145/3357384.3357924
    Locate open access versionFindings
  • Chuxu Zhang, Dongjin Song, Chao Huang, Ananthram Swami, and Nitesh V. Chawla. 2019. Heterogeneous Graph Neural Network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, August 4-8, 2019. 793–803.
    Google ScholarLocate open access versionFindings
Full Text
Your rating :
0

 

Tags
Comments