Sales Forecasting for Fashion Retailing Service Industry: A Review

Table 1

The summary of AI methods-based fashion retail sales forecasting.

Method	Paper	Area	Findings
ANN	[3]	Sufficient data	ANN model outperforms the two statistical based models.
Fuzzy	[15]	Short term; Sufficient data	Multivariate fuzzy analysis is better compared to that of univariate analysis for short term forecasting.
	[28]	Color	Fuzzy colour prediction system is better than the traditional approach, but it only applies to single-colour prediction case.
ENN	[19]	Low demand uncertainty and weak seasonal trends; Short term	Performance of ENN is better than the traditional SARIMA model for products with features of low demand uncertainty and weak seasonal trends.
ELM	[31]	Color, size, and price as significant factors	ELM outperforms several sales forecasting methods which are based on backpropagation neural networks.
EELM	[32]	Fast forecasting	EELM is versatile in which it can be used for short, medium to long-term predictions with both time series and non-time series data.