Abstract
In today’s rapidly changing and highly competitive industrial environment, a new and emerging business model—fast fashion—has started a revolution in the apparel industry. Due to the lack of historical data, constantly changing fashion trends, and product demand uncertainty, accurate demand forecasting is an important and challenging task in the fashion industry. This study integrates k-means clustering (KM), extreme learning machines (ELMs), and support vector regression (SVR) to construct cluster-based KM-ELM and KM-SVR models for demand forecasting in the fashion industry using empirical demand data of physical and virtual channels of a case company to examine the applicability of proposed forecasting models. The research results showed that both the KM-ELM and KM-SVR models are superior to the simple ELM and SVR models. They have higher prediction accuracy, indicating that the integration of clustering analysis can help improve predictions. In addition, the KM-ELM model produces satisfactory results when performing demand forecasting on retailers both with and without physical stores. Compared with other prediction models, it can be the most suitable demand forecasting method for the fashion industry.
Highlights
The fashion industry has evolved and greatly transformed in the past two decades [1,2].The current developing trend is to vertically integrate the supply chain to shorten the response time and quickly respond to customer needs
This study uses extreme learning machines (ELMs), support vector regression (SVR), k-means clustering (KM)-ELM, and KM-SVR models for demand forecasting to find the best prediction models between them
The authors of [23] indicated that the most important ELM parameter is the number of hidden nodes, and ELM tends to be unstable in single run forecasting
Summary
The fashion industry has evolved and greatly transformed in the past two decades [1,2]. As pointed out in previous studies [6], the fashion industry has highly complex data patterns, which makes it difficult for traditional statistical methods to produce good prediction results. The usage of ELM and SVR further shortens the time needed to process highly complex demand data for the fashion industry and model construction. This research proposes two fast fashion industry demand forecasting models based on clustering analysis: the prediction model that integrates k-means (KM) and ELM (the KM-ELM prediction model) and the prediction model that integrates KM and SVR KM-SVR prediction model) to meet the fast fashion industry needs of demand forecasting. There are very few cluster-based machine learning prediction models that are applied to demand forecasting of the fast fashion industry in the past.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
