The fashion apparel industry is too diverse, volatile and uncertain due to the fast changing market scenario. Forecasting demands of consumers has become survival necessity for organizations dealing with this field. Many traditional approaches have been proposed for improving the computational time and accuracy of the forecasting system. However, most of the approaches have over-looked the uncertainty existing in the fashion apparel market due to certain unpredictable events such as new trends, new promotions and advertisements, sudden rise and fall in economic conditions and so on. In this chapter, an intelligent multi-agent based demand forecasting and replenishment system has been proposed that adopts features from nature-inspired computing for handling uncertainty of the fashion apparel industry. The proposed system is inspired from the group hunting behaviour of crocodiles such as they form temporary alliances with other crocodiles for their own benefit even after being territorial creatures.
TopIntroduction
The apparel industry has been going through continuous transitional phases since last few decades. With the increase in the availability of variety in almost all product lines produced by various competitors in the global market segments, the competition among various organisations has been elevated dramatically. In order to survive this global competition, the organizations have adopted faster and flexible product manufacturing systems. But in spite of these adoptions, the organizations are facing many challenges in their attempt to acquire the continuously changing market of apparel industry. Moreover, Apparel industry is inherently diverse and heterogeneous in nature. Some of the factors responsible for the volatile nature of the apparel industry market include (i)globalization of production as well as retailing, (ii) the fast growing instantaneous knowledge about changing trends and brands, (iii) dynamically changing customer requirements leading to segmentation of fashion market (iv) advancement in technology such as automation of several processes across the value chain, (v) information sharing among manufacturers, wholesalers, and retailers and finally (vi) the need for reducing the price of final products to keep pace with the highly competitive market (Marufuzzaman et. al, 2009; Chan and Chan, 2010; Rayman et. al, 2011; Sekozawa et.al, 2011; D'Amico, et al., 2013). Therefore in order to match the rapidly changing environment of the fashion market, the organizations existing in the apparel industry have to be more flexible and responsive.
With the increase in fashion trend consciousness among consumers as a by-product of continuously changing lifestyle and economic conditions, satisfying varying consumer needs has become a survival challenge for most organizations dealing with apparel industry. Instead of producing products in bulk with standardized styles and trends as they used to do previously, organizations now try to refresh their products frequently maintaining uniqueness to survive in the competitive fashion industry. This decision of frequent refreshing of products depends on many factors such as seasons, social events, festivals, trends, locality and many more, so as to predict which kind of fashion products will be in peak demand during which period of the year. In other words, the fragmented market of the apparel industry has now been shifted from product-driven to consumer demand-driven type.
One of the most crucial challenges faced for the smooth operation of apparel industry is to forecast the continuously fluctuating demand of the consumers so as to plan the production of the products. The major characteristics of the products of apparel industry that makes demand forecasting challenging include (i) short duration of selling periods i.e., selling seasons, (ii) balancing the relation between selling seasons and product replenishment, (iii) product life cycle . Although, most of the organisations in apparel industry spend a major portion of their revenue to research various forecasting approaches and tools to predict real-time demands but still mostly fail due to high level of complexity and openness of fashion markets. In today’s competitive scenario, demand forecasting plays a significant role in the smooth and efficient execution of production plan, but however, forecasting fails many times due to poor forecasting resulting from the existence of uncertainty and volatility in the consumer demands. This uncertainty in demand forecast occurs due to many co-existing factors such as availability of partial historical data, seasonal trends or any uncertain events and leads to erroneous product planning, manufacturing and distribution. Moreover, inaccuracy in demand forecasts can cost organizations heavily in terms of high inventory with unwanted goods to be sold at a low price or even at loss, stock outs resulting in loss of potential customers due to unavailability of desired products in stock, poor customer service, rush orders due to hike in demand of any particular product and poor utilization of resources. Therefore, to avail the competitive advantage over others, organisations must improve their demand forecasting systems which should be capable of adapting to the highly volatile and uncertain fashion markets.