Abstract
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.
Original language | English |
---|---|
Title of host publication | Proceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011 |
Pages | 1010-1014 |
Number of pages | 5 |
Volume | 3 |
DOIs | |
Publication status | Published - 7 Nov 2011 |
Event | 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011 - Guilin, Guangxi, China Duration: 10 Jul 2011 → 13 Jul 2011 |
Conference
Conference | 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011 |
---|---|
Country/Territory | China |
City | Guilin, Guangxi |
Period | 10/07/11 → 13/07/11 |
Keywords
- fashion
- fast forecasting
- Intelligent forecasting
- research agenda
- sales forecasting
ASJC Scopus subject areas
- Artificial Intelligence
- Computational Theory and Mathematics
- Computer Networks and Communications
- Human-Computer Interaction