Abstract
Color trends are fickle components of clothing styles. It’s a tough task to predict trendy colors for the fashion industry. Meanwhile, excess inventory of certain colors and stock out of popular colors both lead to extra costs. Intense competition and short product life cycles require fashion apparel retailers to be flexible and responsive to the change of market trends. As a consequence of limited historical data, many studies focus on employing advanced and hybrid models to improve forecasting accuracy. These studies ignore abundant user interaction data on social media, which is an important source to understand consumer need, as well as advanced methods to deal will multivariate data in the forecasting model. Thus, this study aims to fill this research gap by applying Bayesian Neural Networks model and incorporating user interaction data, especially emojis, into the model. The evaluation results show that Bayesian Neural Networks outperform baseline model (Neural Networks and Support Vector Regression) and the model with emoji performs better than the one without emoji. The paper demonstrates the predictive value of emoji and provides an advanced method to process multivariate data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Moore, M., Fairhurst, A.: Marketing capabilities and firm performance in fashion retailing. J. Fashion Mark. Manag. Int. J. 7(4), 386–397 (2003)
Yu, Y., Hui, C.L., Choi, T.M.: An empirical study of intelligent expert systems on forecasting of fashion color trend. Expert Syst. Appl. 39(4), 4383–4389 (2012)
Kosinski, M., Stillwell, D., Graepel, T.: Private traits and attributes are predictable from digital records of human behavior. Proc. Nat. Acad. Sci. USA 110, 5802–5805 (2013)
Chan, C.S.: Can style be measured? Des. Stud. 21(3), 277–291 (2000)
Yu, Y., Choi, T.M., Hui, C.L., Ho, T.K.: A new and efficient intelligent collaboration scheme for fashion design. IEEE Trans. Syst. Man Cybern.-Part A Syst. Hum. 41(3), 463–475 (2011)
Sun, Z.L., Choi, T.M., Au, K.F., Yu, Y.: Sales forecasting using extreme learning machine with applications in fashion retailing. Decis. Support Syst. 46(1), 411–419 (2008)
Miller, H., Thebault-Spieker, J., Chang, S., Johnson, I., Terveen, L., Hecht, B.: “Blissfully happy” or “ready to fight”: Varying Interpretations of Emoji. In: Proceedings of ICWSM (2016)
Eisner, B., Rocktäschel, T., Augenstein, I., Bošnjak, M. Riedel, S.: emoji2vec: Learning Emoji Representations from their Description. arXiv preprint arXiv:1609.08359 (2016)
Dresner, E., Herring, S.: Functions of the nonverbal in CMC: emoticons and illocutionary force. Commun. Theor. 20(3), 249–268 (2010)
Vidal, L., Ares, G., Jaeger, S.R.: Use of emoticon and emoji in tweets for food-related emotional expression. Food Qual. Prefer. 49, 119–128 (2016)
Winters, P.R.: Forecasting sales by exponentially weighted moving averages. Manag. Sci. 6(3), 324–342 (1960)
Alon, I., Qi, M., Sadowski, R.J.: Forecasting aggregate retail sales: a comparison of artificial neural networks and traditional methods. J. Retail. Consum. Ser. 8(3), 147–156 (2001)
Choi, T.M., Hui, C.L., Ng, S.F., Yu, Y.: Color trend forecasting of fashionable products with very few historical data. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 42(6), 1003–1010 (2012)
Li, W., Chau, M.: The predictive power of online user engagement on product sales. In: Proceedings of the Workshop on E-Business (WEB 2017), Seoul, South Korea (2017)
Frank, C., Garg, A., Sztandera, L., Raheja, A.: Forecasting women’s apparel sales using mathematical modeling. Int. J. Clothing Sci. Technol. 15(2), 107–125 (2003)
Cui, D., Curry, D.: Prediction in marketing using the support vector machine. Mark. Sci. 24(4), 595–615 (2005)
West, P.M., Brockett, P.L., Golden, L.L.: A comparative analysis of neural networks and statistical methods for predicting consumer choice. Mark. Sci. 16(4), 370–391 (1997)
Denker, J., et al.: Large automatic learning, rule extraction, and generalization. Complex Syst. 1(5), 877–922 (1987)
Hernández-Lobato, J.M. Adams, R.: Probabilistic backpropagation for scalable learning of bayesian neural networks. In: International Conference on Machine Learning, pp. 1861–1869 (2015)
Xiong, H.Y., Barash, Y., Frey, B.J.: Bayesian prediction of tissue-regulated splicing using RNA sequence and cellular context. Bioinformatics 27(18), 2554–2562 (2011)
Utama, R., Piekarewicz, J., Prosper, H.B.: Nuclear mass predictions for the crustal composition of neutron stars: a Bayesian neural network approach. Phys. Rev. C 93, 014311 (2016)
Acknowledgements
The authors thank to reviewers and colleagues for their constructive comments on the paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, W., Chau, M. (2019). Color Trend Forecasting with Emojis. In: Xu, J., Zhu, B., Liu, X., Shaw, M., Zhang, H., Fan, M. (eds) The Ecosystem of e-Business: Technologies, Stakeholders, and Connections. WEB 2018. Lecture Notes in Business Information Processing, vol 357. Springer, Cham. https://doi.org/10.1007/978-3-030-22784-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-22784-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22783-8
Online ISBN: 978-3-030-22784-5
eBook Packages: Computer ScienceComputer Science (R0)