推荐系统对消费者网购支出的影响研究

doi:10.16381/j.cnki.issn1003-207x.2020.06.015

Abstract

Abstract: The recommendation system, with information filtering technology, is used to recommend products and services of interest to consumers in e-commerce. The relationship between consumers’ online shopping behaviors, including preferences and loyalty, and their personal attributes such as age, gender and region is analyzed by collecting a large number of questionnaires concerning online shopping with which the reliability and validity requirement for data analysis are met. Propensity Score Matching Method (PSM) is used to study the impact of using recommendation system on expenditure of online shopping. Instrumental Variables Method (IV) is conducted to test the robustness of PSM research results. The results show that the consumer online shopping expenditure using the recommendation system is 14.7% higher than that of the unused one.Online shopping spending is positively correlated with education and income, and negatively correlated with age.Urban consumers and women are more willing to use the recommendation system.Generally, recommendation effect is affected by social relations,complementary products, store reputation. The research results play an important role in assessing the economic benefits of recommendation system, promoting recommendation system to help consumers purchase satisfactory products, and enhancing consumer loyalty.

Key words: consumer online shopping expenditure, recommendation system, propensity score matching method, instrumental variables method

CLC Number:

F724.6

HU Chun-hua, ZHAO Hui, TONG Xiao-qin, REN Jian. Research on the Impact of Intelligent Recommendation System on Consumer Online Shopping[J]. Chinese Journal of Management Science, 2020, 28(6): 158-170.

References

[1] Chen Min. Improving website structure through reducing information overload[J]. Decision Support Systems, 2018, 110(6):84-94.
[2] Di Noia T, Rosati J, Tomeo P, et al. Adaptive multi-attribute diversity for recommender systems[J]. Information Sciences, 2017, 382-383(3):234-253.
[3] 阿里巴巴集团双11技术团队. 尽在双11-阿里巴巴技术演进与超越[M]. 北京:电子工业出版社, 2017.
[4] 刘尚堃.京东数据驱动下的个性化推荐系统[OL].[2019-05-28], https://doc.mbalib.com/view/77b0b4bd4cb6873aefcf3970fde463a1.html.
[5] Smith B, Linden G. Two decades of recommender systems at amazon.com[J]. IEEE Internet Computing, 2017, 21(3):12-18.
[6] Herlocker J L, Konstan J A, Borchers A, et al. An algorithmic framework for performing collaborative filtering[J]. ACM Sigir Forum, 2017, 51(2):227-234.
[7] 项亮.推荐系统实践[M].北京:人民邮电出版社, 2017.
[8] Adomavicius G, Bockstedt J C, Curley S P, et al. Effects of online recommendations on consumers' willingness to pay[J]. Information Systems Research, 2012, 893(1):40-45.
[9] 黄立威,江碧涛,吕守业,等. 基于深度学习的推荐系统研究综述[J]. 计算机学报, 2018, 41(7):1619-1641.
[10] Sharma A, Hofman J.M, Watts D.J. Estimating the causal impact of recommendation systems from observational data[C]//Proceedings of the sixteenth ACM International Conference on Economics and Computation, Oregon, USA, June 15-19, ACM, 2015:453-470.
[11] Brad Stone. The everything store:Jeff Bezos and the age of Amazon[M]. New York:Little Brown and Company, 2013.
[12] Nazerzadeh H, Saberi A, Vohra R. Dynamic pay-per-action mechanisms and applications to online advertising[J]. Operations Research, 2013, 61(1):98-111.
[13] Davis J A. Measuring marketing:110+ key metrics every marketer needs, second edition[M]. John Wiley & Sons, Inc, 2013.
[14] Chaudhari M B, Dietrich S W, Ortiz J. Spencer pearson towards a hybrid relational and XML benchmark for loosely-coupled distributed data sources[J]. Journal of Systems and Software, 2015, 109(11):78-87.
[15] Geng Bingrui, Jiao Licheng, Gong Maoguo, et al.A two-step personalized location recommendation based on multi-objective immune algorithm[J]. Information Sciences, 2019, 475(2):161-181.
[16] Guo Taolin, Luo Junzhou, Dong Kai, et al. Differentially private graph-link analysis based social recommendation[J]. Information Sciences, 2018, 463-464(10):214-226.
[17] Bach N X, Hai N D, Phuong T M. Personalized recommendation of stories for commenting in forum-based social media[J]. Information Sciences, 2016, 352-353(10):48-60.
[18] Xiao B, Benbasat I. An empirical examination of the influence of biased personalized product recommendations on consumers' decision making outcomes[J]. Decision Support Systems, 2018, 110(3):46-57.
[19] Chen Yanhong, Lu Yaobin, Wang Bin.How do product recommendations affect Impulse buying? An empirical study on WeChat social commerce[J]. Information & Management,2019, 56(9):236-248.
[20] 张哲宇, 罗彪, 梁樑. 网络环境下的消费者态度转变——基于在线口碑信息框架交互作用的实验研究[J]. 管理科学学报, 2018, 21(11):23-39.
[21] 郝玫,马建峰.在线评论中基于动态窗口提取特征观点对的产品推荐模型[J].系统工程理论与实践,2018,38(9):2363-2375.
[22] 尹进,胡祥培,郑毅,等.社会化商务中基于经验及推荐的消费者感知信任模糊融合模型[J]. 中国管理科学, 2020, 28(1):122-133.
[23] 姚凯,涂平, 陈宇新, 等. 基于多源大数据的个性化推荐系统效果研究[J].管理科学, 2018, 31(5):7-19.
[24] Baier D,Stüber E. Acceptance of recommendations to buy in online retailing[J].Journal of Retailing and Consumer Services, 2010, 17(3):173-180.
[25] Lee K C, Kwon S. Online shopping recommendation mechanism and its influence on consumer decisions and behaviors:A causal map approach[J]. Expert Systems with Applications, 2008, 35(4):1567-1574.
[26] Zhang H, Zhao L, Gupta S. The role of online product recommendations on customer decision making and loyalty in social shopping communities[J].International Journal of Information Management, 2017, 38(10):150-166.
[27] 汪潜, 申德荣, 冯朔,等. 全视角特征结合众包的跨社交网络用户识别[J].软件学报, 2018, 29(3):811-823.
[28] Herlocker J L, Konstan J A, Terveen L G, et al. Evaluating collaborative filtering recommender systems[J]. ACM Transactions on Information Systems, 2004, 22(1):5-53.
[29] 胡川, 孟祥武, 张玉洁, 等.一种改进的偏好融合组推荐方法[J].软件学报, 2018,29(10):3164-3183.
[30] 景楠,王建霞,许皓,等.基于用户社会关系的社交网络好友推荐算法研究[J].中国管理科学,2017, 25(3):164-171.
[31] Dabholkar P A, Sheng X. Consumer participation in using online recommendation agents:Effects on satisfaction, trust, and purchase intention[J]. ServiceIndustriesJournal, 2012, 32(9):1433-1449.
[32] Liu Chienliang, Chen Yingchuan. Background music recommendation based on latent factors and moods[J]. KnowledgeBased Systems, 2018, 159(11):158-170.
[33] Sarwar B, Karypis G, Konstan J. Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International Conference on World Wide Web. New York, May 1-5, ACM Press, 2001:285-295.
[34] Zhang Qian, Wu Dianshuang, Lu Jie, et al. A crossdomain recommender system with consistent information transfer[J]. Decision Support Systems, 2017, 104(12):49-63.
[35] Fleder D,Hosanagar K.Blockbuster culture's next rise or fall:The impact of recommender systems on sales diversity[J].Management Science, 2009, 55(5):697-712.
[36] Schreiner T, Rese A, Baier D. Multi-channel personalization:Identifying consumer preferencesfor product recommendations in advertisements across different media channels[J].Journal of Retailing and Consumer Services, 2019, 48(2):87-99.
[37] 吕苗, 金淳, 韩庆平. 基于情境化用户偏好的协同过滤推荐模型[J].系统工程理论与实践, 2016,36(12):3244-3254.
[38] 张立功, 郭晓龙, 韩东亚,等. 考虑消费者网购体验滞后的产品定价研究[J]. 中国管理科学, 2019, 27(3):77-84.
[39] 朱志国,周雨禾,王谢宁.移动商务中融合签到位置与用户间相似性的兴趣点精准推荐[J]. 系统工程理论与实践, 2020,40(2):462-469.
[40] 胡春华,童小芹,梁伟.基于信任和不信任关系的实值受限玻尔兹曼机推荐算法[J].系统工程理论与实践, 2019, 39(7):1812-1825.
[41] Bejarano H, Green E P, Rassenti S, et al. Payment scheme self-selection in the credence goods market:An experimental study[J]. Journal of Economic Behavior & Organization, 2017, 142(10):396-403.
[42] Maghrabi R O, Oakley R L, Nemati H R. The impact of self-selected identity on productive or perverse social capital in social network sites[J]. Computers in Human Behavior, 2014, 33(4):367-371.
[43] Rosenbaum P R, Rubin D B. The central role of the propensity score in observational studies for causal effects[J]. Biometrika, 1983, 701:41-55.
[44] Wooldridge J M. Econometric analysis of cross section and panel data[M]. MIT press, 2010.
[45] Glenn J M, Galey M, Edwards A, et al. Validity and reliability of the abdominal test and evaluation systems tool (ABTEST) to accurately measure abdominal force[J]. Journal of Science and Medicine in Sport, 2015,18(4):457-462.
[46] Heckman J J, Ichimura H, Todd P. Matching as an econometric evaluation estimator:evidence from evaluating a job training program[J]. Review of Economic Studies, 1998, 65(2):261-294.
[47] Kahneman D, Slovic P, Tversky A. Judgement under uncertainty[M]. New York:Cambridge University Press. 1982.
[48] Caliendo M, Kopeinig S. Some practical guidance for the implementation of propensity scorematching[J]. Journal of Economic Surveys, 2010, 22(1):31-72.
[49] Becker S O, Ichino A. Estimation of average treatment effects based on propensity scores[J]. Stata Journal, 2002, 2(4):358-377.

Research on the Impact of Intelligent Recommendation System on Consumer Online Shopping

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 3

Metrics

Comments

Recommended 10

[1]	CHANG Le, LIU Chang-yu, YU Tao, SUN Zhen-kai. Food Fraud Tripartite Evolutionary Game in Social Co-regulation [J]. Chinese Journal of Management Science, 2020, 28(9): 221-230.
[2]	WANG Chong, CHEN Da-feng. Study of Community Relationship of Multi-dimension Factors Influencing Consumer Purchase Decision-making in O2O Mode [J]. Chinese Journal of Management Science, 2019, 27(1): 110-119.
[3]	WANG Chong, LIU Jian, WU Jia-bao. Building and Research on Consumer’s Perceived Utility Model in Network Environment [J]. Chinese Journal of Management Science, 2011, 19(3): 94-102.