Abstract
While researchers have proposed a large number of sales forecasting models for seasonal products, these models may not work well at the extent of individual products in practice. In this research, based on the popular Prophet model, we propose a practical framework named FS-Prophet to forecast Stock Keeping Unit (SKU) level seasonal sales. In comparison with previous models, our framework incorporates critical background information and therefore shows superior performance especially in the post-sale periods. The proposed methodology has been implemented in JD.com, one of the largest online retailers in China, and a representative experiment based on JD's real data reports a 20.79% increase in terms of weighted mean absolute percentage error compared with the Prophet algorithm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
