A Data-Driven Forecasting Approach for Newly Launched Seasonal Products by Leveraging Machine-Learning Approaches
Name
10479_2020_3666_ReferencePDF.pdf
Size
615.31 KB
Format
Unknown
Checksum (MD5)
95443e4eb480bfb1cecb3627e1b1d455
Author(s)
Kharfan, Majd
Chan, Vicky Wing Kei
Firdolas Efendigil, Tugba
Date Issued
June 2020
Publisher
Springer US
Version
Author's final manuscript
Abstract
Companies in the fashion industry are struggling with forecasting demand due to the short-selling season, long lead times between the operations, huge product variety and ambiguity of demand information. The forecasting process is becoming more complicated by virtue of evolving retail technology trends. Demand volatility and speed are highly affected by e-commerce strategies as well as social media usage regards to varying customer preferences, short product lifecycles, obsolescence of the retail calendar, and lack of information for newly launched seasonal items. Consumers have become more demanding and less predictable in their purchasing behavior that expects high quality, guaranteed availability and fast delivery. Meeting high expectations of customers’ initiates with proper demand management. This study focuses on demand prediction with a data-driven perspective by both leveraging machine learning techniques and identifying significant predictor variables to help fashion retailers achieve better forecast accuracy. Prediction results obtained were compared to present the benefits of machine learning approaches. The proposed approach was applied by a leading fashion retail company to forecast the demand of newly launched seasonal products without historical data.
MIT Department
Massachusetts Institute of Technology. Center for Transportation & Logistics
Massachusetts Institute of Technology. Supply Chain Management Program
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s10479-020-03666-w
