'Recent Trends in Utilization of Fiber, Yarn, Fabrics and Computer Technology in Fashion Designing and Management'
Recent trends in fiber, yarn and fabric management in Textile-Apparel-Distribution network require a very accurate estimation of consumption pattern and sourcing management to minimize their costs and satisfy their customers. For such strategy, fashion designers rely more on fashion forecasting system to respond to the versatile textile market. However, the specific constraints of the textile consumption and sales (numerous and new items, short lifetime) complicate the forecasting procedure and distributors prefer to use intuitive estimation methods of the sales rather than the existing forecasting models.
In this paper we firstly discuss the different aspects used for improving the accuracy of fashion product development and forecasting process, use of computer technology in management of fiber, yarn and fabrics for estimation of their consumption. We also demonstrate a decision aid system, based on neural networks, which automatically performs item sales forecasting of textile items with two models being demonstrated for silk fabric consumption and cotton-textiles fabric consumption. Performances of our model are evaluated using real data released by authorized agencies. Network forecasted results show excellent correlation with real data emphasizing the its advantages over traditionally, statistical time series methods like moving average, auto-regression or combinations of them used for forecasting apparel and fashion product sales.
Keywords: Fashion forecasting, 2-D and 3-D cad system, Neural Network forecasting model, time series, Texture mapping.
Introduction
Introducing new products of Apparels made from different variations of fibers, yarns and fabrics can provide a competitive advantage as well as a long-term financial return on investment. New product development is thus vitally linked to a company's competitive strategy and consequently to the new product sales forecasting of apparels and textiles that provides quantitative information on the expected return from development efforts. Sales forecasting of apparels and textiles attempts to decrease uncertainty, providing input for the decisions made about introducing of new products and offering feedback for the new product development process. The significant correlation between new product development and new product sales forecasts makes new product forecasting extremely important.
Traditionally, statistical time series methods like moving average, auto-regression or combinations of them are used for forecasting fashion trends and sales of fashion products. Since these models predict future sales only on the basis of previous sales, they fail in environments where sales are heavily influenced by exogenous variables, such as economic conditions, climatic conditions, competitive activities, advertising and several factors. Although traditional statistical models characterize the above mentioned factors, they are essentially linear in nature and don't characterize the nonlinear nature of apparel sales and analyse fibre, yarn, fabric consumption trends.
Fuzzy logic, artificial neural networks coupled with latest applications of computer technology for fashion design and management and genetic algorithms(Gas) offer an alternative approach by taking into account both endogenous and exogenous variables and allowing arbitrary non-linear approximation functions derived(learned directly from the previous data).