JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

E-commerce business model mining and prediction

Author(s): Zhou-zhou He, Zhong-fei Zhang, Chun-ming Chen, Zheng-gang Wang
Affiliation(s): Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China; more
Corresponding email(s): zhouzhouhe@zju.edu.cn, zhongfei@zju.edu.cn, chunming.chencm@taobao.com, zhenggang.wangzg@alibabainc.com
Key Words: E-commerce, Business model prediction, Consumer influence, Social network, Sales prediction

Share this article to： More \|Next Paper >>>

Zhou-zhou He, Zhong-fei Zhang, Chun-ming Chen, Zheng-gang Wang. E-commerce business model mining and prediction[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.1500148

@article{title="E-commerce business model mining and prediction",
author="Zhou-zhou He, Zhong-fei Zhang, Chun-ming Chen, Zheng-gang Wang",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.1500148"
}

%0 Journal Article
%T E-commerce business model mining and prediction
%A Zhou-zhou He
%A Zhong-fei Zhang
%A Chun-ming Chen
%A Zheng-gang Wang
%J Frontiers of Information Technology & Electronic Engineering
%P 707-719
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.1500148"

TY - JOUR
T1 - E-commerce business model mining and prediction
A1 - Zhou-zhou He
A1 - Zhong-fei Zhang
A1 - Chun-ming Chen
A1 - Zheng-gang Wang
J0 - Frontiers of Information Technology & Electronic Engineering
SP - 707
EP - 719
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.1500148"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: We study the problem of business model mining and prediction in the e-commerce context. Unlike most existing approaches where this is typically formulated as a regression problem or a time-series prediction problem, we take a different formulation to this problem by noting that these existing approaches fail to consider the potential relationships both among the consumers (consumer influence) and among the shops (competitions or collaborations). Taking this observation into consideration, we propose a new method for e-commerce business model mining and prediction, called EBMM, which combines regression with community analysis. The challenge is that the links in the network are typically not directly observed, which is addressed by applying information diffusion theory through the consumer-shop network. Extensive evaluations using Alibaba Group e-commerce data demonstrate the promise and superiority of EBMM to the state-of-the-art methods in terms of business model mining and prediction.

Abstract: In this paper, the authors have studied the problem of business model mining and prediction in the e-commerce context. Unlike the most existing approaches in the literature where this problem is typically formulated as a regression problem or as a time-series prediction problem, the authors of this paper have developed a different formulation to this problem by noting that these existing approaches fail to consider the potential relationships existing both among the consumers (consumer influence) and among the shops (competitions or collaborations). Authors did an excellent innovation on the methodology.

应用于电子商务环境的商业模式挖掘和预测方法

目的：随着电子商务的发展，商品交易形式发生了翻天覆地的变化。在这种新型虚拟交易平台上，消费者快速而又广泛地浏览、购买、评价各种价廉物美的商品，而商品也同样地进行着产品创新、营销拓展、物流改善。所以，消费者和商品之间早已不是简单的一对一直接买卖关系，而是消费者和消费者之间的社交网络，消费者和商品之间的交易网络构成电子商务中最重要的物质载体。于是，对于商品销量预测这一传统经济问题，在电子商务的大环境下有了新型的研究意义。为了能有效和深入地研究在电子商务环境下的商品销量发展模式，本文的目的在于提供一种应用于电子商务的商品销量预测算法，该算法注重于从消费者社会影响力分析入手，更好地适应真实电子商务环境中的销量预测需求。
创新点：首先，本文算法不仅考虑到消费者自身的特征，同时还考虑到存在于消费者之间的社会影响力，考虑到在真实的电子商务中，消费者之间传递商品的价格信息或评价信息十分便捷，因而本文算法很好地切合了实际的应用环境。其次，本文算法定义了交易环境中的两种社会影响力，即“同一商品中消费者互相作用产生的影响力”和“不同商品之间消费者互相作用产生的影响力”，分别考虑到单一商品的交易环境和多个商品互相作用的交易环境中消费者行为，其中以上两种社会影响力都是由真实消费者社交网络分析提炼得来的，使得本算法更加切合真实交易网络的内在结构。
方法：本文算法将商品销量分为主体部分和噪声部分，很好地模拟了真实交易环境中，商品销量的构成是受多成分影响的。并且在预测模型中，对主体部分和噪声部分分别设置了不同的约束条件，具体为要求商品销量的主体部分在时间上应该保持平滑性，并要求商品销量的噪声部分是稀疏的，以上两个约束很好地反映了真实交易环境中商品销量的变化形式。
结论：本文研究电子商务环境下商品销量的发展模式，并提出描述消费者之间关系的两种社会影响力网络。将此社会影响力网络整合入商品销量构成模型中，最后提出对这些商品销量的预测算法。特别是通过在真实的数据环境中（阿里巴巴女装数据）进行算法测试，并结合与传统销量预测算法的比较，展示在复杂数据环境下本算法的有效性。

关键词组：电子商务；商业模式预测；消费者影响力；社会网络；销量预测

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Anagnostopoulos, A., Kumar, R., Mahdian, M., 2008. Influence and correlation in social networks. Proc. 14th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.7-15.

[2]Anagnostopoulos, A., Brova, G., Terzi, E., 2011. Peer and authority pressure in information-propagation models. LNCS, 6911:76-91.

[3]Bakshy, E., Hofman, J.M., Mason, W.A., et al., 2011. Everyone’s an influencer: quantifying influence on Twitter. Proc. 4th ACM Int. Conf. on Web Search and Data Mining, p.65-74.

[4]Bakshy, E., Rosenn, I., Marlow, C., et al., 2012. The role of social networks in information diffusion. Proc. 21st Int. Conf. on World Wide Web, p.519-528.

[5]Bernstein, M.S., Bakshy, E., Burke, M., et al., 2013. Quantifying the invisible audience in social networks. Proc. SIGCHI Conf. on Human Factors in Computing Systems, p.21-30.

[6]Bhagat, S., Goyal, A., Lakshmanan, L.V.S., 2012. Maximizing product adoption in social networks. Proc. 5th ACM Int. Conf. on Web Search and Data Mining, p.603-612.

[7]Bonchi, F., Castillo, C., Gionis, A., et al., 2011. Social network analysis and mining for business applications. ACM Trans. Intell. Syst. Technol., 2(3), Article 22.

[8]Box, G.E.P., 2008. Time Series Analysis: Forecasting and Control. Wiley.

[9]Boyd, S., Parikh, N., Chu, E., et al., 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn., 3(1):1-122.

[10]Cha, M., Haddadi, H., Benevenuto, F., et al., 2010. Measuring user influence in Twitter: the million follower fallacy. Proc. 4th Int. AAAI Conf. on Weblogs and Social Media, p.10-17.

[11]Cui, P., Jin, S.F., Yu, L.Y., et al., 2013. Cascading outbreak prediction in networks: a data-driven approach. Proc. 19th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.901-909.

[12]Dholakia, U.M., Bagozzi, R.P., Pearo, L.K., 2004. A social influence model of consumer participation in network- and small-group-based virtual communities. Int. J. Res. Market., 21(3):241-263.

[13]Donoho, D.L., Johnstone, I.M., 1995. Adapting to unknown smoothness via wavelet shrinkage. J. Am. Statist. Assoc., 90(432):1200-1224.

[14]Duong, Q., Wellman, M.P., Singh, S.P., 2011. Modeling information diffusion in networks with unobserved links. SocialCom/PASSAT, p.362-369.

[15]Eagle, N., Pentland, A., Lazer, D., 2009. Inferring friendship network structure by using mobile phone data. PNAS, 106(36):15274-15278.

[16]Friedman, J., Hastie, T., Höfling, H., et al., 2007. Pathwise coordinate optimization. Ann. Appl. Statist., 1(2):302-332.

[17]Gomez-Rodriguez, M., Schölkopf, B., 2012. Influence maximization in continuous time diffusion networks. Int. Conf. on Machine Learning.

[18]Gomez-Rodriguez, M., Leskovec, J., Krause, A., 2010. Inferring networks of diffusion and influence. Proc. 16th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.1019-1028.

[19]Guille, A., Hacid, H., Favre, C., et al., 2013. Information diffusion in online social networks: a survey. ACM SIGMOD Rec., 42(1):17-28.

[20]Hoefling, H., 2010. A path algorithm for the fused lasso signal approximator. J. Comput. Graph. Statist., 19(4):984-1006.

[21]Long, B., Zhang, Z.F., Yu, P.S., 2007. A probabilistic framework for relational clustering. Proc. 13th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.470-479.

[22]Myers, S.A., Leskovec, J., 2012. Clash of the contagions: cooperation and competition in information diffusion. IEEE 12th Int. Conf. on Data Mining, p.539-548.

[23]Myers, S.A., Zhu, C.G., Leskovec, J., 2012. Information diffusion and external influence in networks. Proc. 18th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.33-41.

[24]Onnela, J.P., Reed-Tsochas, F., 2010. Spontaneous emergence of social influence in online systems. PNAS, 107(43):18375-18380.

[25]Romero, D.M., Galuba, W., Asur, S., et al., 2011. Influence and passivity in social media. European Conf. on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, p.18-33.

[26]Saito, K., Ohara, K., Yamagishi, Y., et al., 2011. Learning diffusion probability based on node attributes in social networks. 19th Int. Symp. on Foundations of Intelligent Systems, p.153-162.

[27]Tang, J., Sun, J.M., Wang, C., et al., 2009. Social influence analysis in large-scale networks. Proc. 15th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.807-816.

[28]Tibshirani, R., Saunders, M., Rosset, S., et al., 2005. Sparsity and smoothness via the fused lasso. J. R. Stat. Soc. Ser. B, 67(1):91-108.

[29]Tsur, O., Rappoport, A., 2012. What’s in a hashtag?: content based prediction of the spread of ideas in microblogging communities. Proc. 5th ACM Int. Conf. on Web Search and Data Mining, p.643-652.

[30]Wu, S.M., Hofman, J.M., Mason, W.A., et al., 2011. Who says what to whom on Twitter. Proc. 20th Int. Conf. on World Wide Web, p.705-714.

[31]Yang, J., Leskovec, J., 2010. Modeling information diffusion in implicit networks. IEEE 10th Int. Conf. on Data Mining, p.599-608.

[32]Zhang, Z.F., Salerno, J.J., Yu, P.S., 2003. Applying data mining in investigating money laundering crimes. Proc. 9th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.747-752.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

应用于电子商务环境的商业模式挖掘和预测方法

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference