Off-line Customer Flow Forecast through Deep Neural Networks

Status	已發表Published
	Off-line Customer Flow Forecast through Deep Neural Networks
	Zhang, X. F.; Chen, X. Y.; Dong, C.Y.
	2018-05-21
Source Publication	2018 AMA Global Marketing SIG Conference Proceedings
Abstract	Customer flow forecast is of practical importance in business intelligence domain. This paper particularly investigates an interesting issue, i.e., how to forecast off-line customer flow of over two thousand shops by considering both the online customer behaviors and off-line periodic customer behaviors. Apparently, it is difficult to directly model the unobserved affecting factors via traditional regression models. To this end, the proposed approach first introduces various extra information to incorporate more potential factors. Then, the hierarchical linear model is performed to screen out insignificant factors. On top of the reduced feature space, the second-order flow factor is incorporated to model the variance term constituting to the forecast error. The combined new feature set is then used for the learning of a number of Long Short Term Memory (LSTM) models. The rigorous experiments have been performed and the promising results demonstrate the superiority of the proposed approach which indicates the wide applicability of the proposed forecast model.
Keyword	Off-line customer Flow Forecast Time Series Deep Neural Networks
URL	View the original
Language	英語English
The Source to Article	PB_Publication
PUB ID	41928
Document Type	Conference paper
Collection	University of Macau
Corresponding Author	Zhang, X. F.
Recommended Citation GB/T 7714	Zhang, X. F.,Chen, X. Y.,Dong, C.Y.. Off-line Customer Flow Forecast through Deep Neural Networks[C], 2018.
APA	Zhang, X. F.., Chen, X. Y.., & Dong, C.Y. (2018). Off-line Customer Flow Forecast through Deep Neural Networks. 2018 AMA Global Marketing SIG Conference Proceedings.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh