File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-22784-5_17
- Scopus: eid_2-s2.0-85069170924
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Color Trend Forecasting with Emojis
Title | Color Trend Forecasting with Emojis |
---|---|
Authors | |
Keywords | Bayesian Neural Networks Color trend Emojis |
Issue Date | 2019 |
Publisher | Springer. The Proceedings' web site is located at https://link.springer.com/conference/web |
Citation | The 17th Workshop on e-Business (WeB): The Ecosystem of e-Business: Technologies, Stakeholders, and Connections, Santa Clara, CA, USA, 12 December 2018. In Xu, J ... (et al) (eds) The Ecosystem of e-Business: Technologies, Stakeholders, and Connections (WEB 2018), p. 171-181. Cham: Springer, 2019 How to Cite? |
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. |
Persistent Identifier | http://hdl.handle.net/10722/278796 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.339 |
Series/Report no. | Lecture Notes in Business Information Processing ; v. 357 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | LI, W | - |
dc.contributor.author | Chau, MCL | - |
dc.date.accessioned | 2019-10-21T02:14:12Z | - |
dc.date.available | 2019-10-21T02:14:12Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | The 17th Workshop on e-Business (WeB): The Ecosystem of e-Business: Technologies, Stakeholders, and Connections, Santa Clara, CA, USA, 12 December 2018. In Xu, J ... (et al) (eds) The Ecosystem of e-Business: Technologies, Stakeholders, and Connections (WEB 2018), p. 171-181. Cham: Springer, 2019 | - |
dc.identifier.isbn | 978-3-030-22783-8 | - |
dc.identifier.issn | 1865-1348 | - |
dc.identifier.uri | http://hdl.handle.net/10722/278796 | - |
dc.description.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. | - |
dc.language | eng | - |
dc.publisher | Springer. The Proceedings' web site is located at https://link.springer.com/conference/web | - |
dc.relation.ispartof | 17th Workshop on e-Business, WeB 2018: The Ecosystem of e-Business: Technologies, Stakeholders, and Connections | - |
dc.relation.ispartofseries | Lecture Notes in Business Information Processing ; v. 357 | - |
dc.subject | Bayesian Neural Networks | - |
dc.subject | Color trend | - |
dc.subject | Emojis | - |
dc.title | Color Trend Forecasting with Emojis | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Chau, MCL: mchau@business.hku.hk | - |
dc.identifier.authority | Chau, MCL=rp01051 | - |
dc.identifier.doi | 10.1007/978-3-030-22784-5_17 | - |
dc.identifier.scopus | eid_2-s2.0-85069170924 | - |
dc.identifier.hkuros | 307567 | - |
dc.identifier.spage | 171 | - |
dc.identifier.epage | 181 | - |
dc.identifier.eissn | 1865-1356 | - |
dc.publisher.place | Cham | - |
dc.identifier.issnl | 1865-1348 | - |