Intelligent time series fast forecasting for fashion sales: A research agenda

• Published in: 2011 International Conference on Machine Learning and Cybernetics Vol. 3; pp. 1010 - 1014
• Main Authors: Tsan-Ming Choi, Chi-Leung Hui, Yong Yu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2011
• Subjects: fashion; fast forecasting; Forecasting; Intelligent forecasting; Machine learning; Marketing and sales; Predictive models; research agenda; sales forecasting; Statistical analysis; Time series analysis
• ISBN: 9781457703058; 145770305X
• ISSN: 2160-133X
• DOI: 10.1109/ICMLC.2011.6016870

Forecasting for the time series sales data of fashion products is crucial for many fashion companies. However, both the traditional statistical methods and the more advanced intelligent artificial intelligence (AI) methods suffer serious drawbacks in which the former's performance depend highly on the time series data's features whereas the latter ones are slow. There is hence a need to call for the development of an intelligent time series forecasting system which is fast, versatile and can achieve a reasonably high accuracy. In this paper, we explore this issue and propose a research agenda for future studies around intelligent fast forecasting system for the prediction of fashion sales time series.