Predicting E-commerce Item Sales With Web Environment Temporal Background

Authors

DOI:

https://doi.org/10.52825/bis.v1i.37

Keywords:

e-commerce, recommender, social media

Abstract

In this paper, we study the effect of Web environment temporal background in pre-dicting e-commerce item sales, especially  those in temporary sales. Temporary sales nowadaysare a popular strategy for quickly clearing inventories. For traditional  recommender systems,predicting the sales of an item is done based on its past purchase records. For temporarysales items, however, such records are not available. In order to make recommendation forsuch items, contextual information, such as product descriptions, is usually used. We investi-gate whether temporal background in the Web environment can be additional useful contextualinformation in recommender systems. It is assumed that items consistent with the temporalbackground would have higher demands. We propose a method for representing the temporalbackground using word embeddings of e-commerce activities and social media data, and eval-uate their effect on sales prediction. Through empirical analysis with real-world data, we foundthat temporal background does have positive effects for sales prediction. The findings in thispaper can be conveniently incorporated into future recommender system designs.

Downloads

Download data is not yet available.

References

[AH10] S. Asur and B. A. Huberman, “Predicting the future with social media,” inWebIntelligence and Intelligent Agent Technology (WI-IAT), IEEE, vol. 1, 2010, pp. 492–499.[BMZ11]J. Bollen, H. Mao, and X. Zeng, “Twitter mood predicts the stock market,”Journalof computational science, vol. 2, no. 1, pp. 1–8, 2011.

[CALC13]Y. Chen, H. Amiri, Z. Li, and T.-S. Chua, “Emerging topic detection for organizationsfrom microblogs,” in Proceedings of the 36th international ACM SIGIR conferenceon Research and development in information retrieval, ACM, 2013, pp. 43–52.

[DL18] F. Dilm ́e and F. Li, “Revenue management without commitment: Dynamic pricingand periodic flash sales,”The Review of Economic Studies, 2018.

[GGK+05] D. Gruhl, R. Guha, R. Kumar, J. Novak, and A. Tomkins, “The predictive power ofonline chatter,” in Proceedings of the eleventh ACM SIGKDD international confer-ence on Knowledge discovery in data mining, ACM, 2005, pp. 78–87.

[LCYL18] G. Lai, W.-C. Chang, Y. Yang, and H. Liu, “Modeling long-and short-term temporalpatterns with deep neural networks,” inThe 41st International ACM SIGIR Confer-ence on Research & Development in Information Retrieval, 2018, pp. 95–104.

[LLK14] G. Ling, M. R. Lyu, and I. King, “Ratings meet reviews, a combined approach torecommend,” in Proceedings of the 8th ACM Conference on Recommender sys-tems, ACM, 2014, pp. 105–112.

[LMV14]N. B. Lassen, R. Madsen, and R. Vatrapu, “Predicting iphone sales from iphonetweets,” in Proceeding of the 18th International Enterprise Distributed Object Com-puting Conference, IEEE, 2014, pp. 81–90.

[LVLD08] X. N. Lam, T. Vu, T. D. Le, and A. D. Duong, “Addressing cold-start problem inrecommendation systems,” in Proceedings of the 2nd international conference onUbiquitous information management and communication, 2008, pp. 208–211.

[MCA+13] H. S. Moat, C. Curme, A. Avakian, D. Y. Kenett, H. E. Stanley, and T. Preis, “Quan-tifying wikipedia usage patterns before stock market moves,”Scientific reports,vol. 3, p. 1801, 2013.

[PL18] P.-F. Pai and C.-H. Liu, “Predicting vehicle sales by sentiment analysis of twitterdata and stock market values,”IEEE Access, vol. 6, pp. 57 655–57 662, 2018.

[SKKR01] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl, “Item-based collaborative filteringrecommendation algorithms,” in Proceedings of the 10th International Conferenceon World Wide Web, ACM, 2001, pp. 285–295.

[WB04] Z. Wang and D. A. Bessler, “Forecasting performance of multivariate time seriesmodels with full and reduced rank: An empirical examination,”International Journalof Forecasting, vol. 20, no. 4, pp. 683–695, 2004.

[ZHS20] Y. Zhang, T. Hara, and M. Shirakawa, “Discovering social media timing signals forpredicting temporary deal success.,” in Proceedings of the 28th European Confer-ence on Information Systems, 2020.

[ZP13] Y. Zhang and M. Pennacchiotti, “Predicting purchase behaviors from social media,”in Proceedings of the 22nd international conference on World Wide Web, ACM,2013, pp. 1521–1532.

Published

2021-07-02