Sales demand forecast in E-commerce using a long short-term memory neural network methodology

Kasun Bandara, Peibei Shi, Christoph Bergmeir, Hansika Hewamalage, Quoc Tran, Brian Seaman

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

Generating accurate and reliable sales forecasts is crucial in the E-commerce business. The current state-of-the-art techniques are typically univariate methods, which produce forecasts considering only the historical sales data of a single product. However, in a situation where large quantities of related time series are available, conditioning the forecast of an individual time series on past behaviour of similar, related time series can be beneficial. Since the product assortment hierarchy in an E-commerce platform contains large numbers of related products, in which the sales demand patterns can be correlated, our attempt is to incorporate this cross-series information in a unified model. We achieve this by globally training a Long Short-Term Memory network (LSTM) that exploits the non-linear demand relationships available in an E-commerce product assortment hierarchy. Aside from the forecasting framework, we also propose a systematic pre-processing framework to overcome the challenges in the E-commerce business. We also introduce several product grouping strategies to supplement the LSTM learning schemes, in situations where sales patterns in a product portfolio are disparate. We empirically evaluate the proposed forecasting framework on a real-world online marketplace dataset from Walmart.com. Our method achieves competitive results on category level and super-departmental level datasets, outperforming state-of-the-art techniques.

Original languageEnglish
Title of host publicationNeural Information Processing
Subtitle of host publication26th International Conference, ICONIP 2019 Sydney, NSW, Australia, December 12–15, 2019 Proceedings, Part III
EditorsTom Gedeon, Kok Wai Wong, Minho Lee
Place of PublicationCham Switzerland
PublisherSpringer
Pages462-474
Number of pages13
ISBN (Electronic)9783030367183
ISBN (Print)9783030367176
DOIs
Publication statusPublished - 2019
EventInternational Conference on Neural Information Processing 2019 - Sydney, Australia
Duration: 12 Dec 201915 Dec 2019
Conference number: 26th
http://ajiips.com.au/iconip2019/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11955
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference on Neural Information Processing 2019
Abbreviated titleICONIP 2019
CountryAustralia
CitySydney
Period12/12/1915/12/19
Internet address

Keywords

  • Demand forecasting
  • E-commerce
  • LSTM
  • Time series

Cite this

Bandara, K., Shi, P., Bergmeir, C., Hewamalage, H., Tran, Q., & Seaman, B. (2019). Sales demand forecast in E-commerce using a long short-term memory neural network methodology. In T. Gedeon, K. W. Wong, & M. Lee (Eds.), Neural Information Processing : 26th International Conference, ICONIP 2019 Sydney, NSW, Australia, December 12–15, 2019 Proceedings, Part III (pp. 462-474). (Lecture Notes in Computer Science ; Vol. 11955). Springer. https://doi.org/10.1007/978-3-030-36718-3_39