Kin-Fan Au

Sales forecasting using extreme learning machine with applications in fashion retailing

Sales forecasting is a challenging problem owing to the volatility of demand which depends on many factors. This is especially prominent in fashion retailing where a versatile sales forecasting system is crucial. This study applies a novel neural network technique called extreme learning machine (ELM) to investigate the relationship between sales amount and some significant factors which affect demand (such as design factors). Performances of our models are evaluated by using real data from a fashion retailer in Hong Kong. The experimental results demonstrate that our proposed methods outperform several sales forecasting methods which are based on backpropagation neural networks.

Empirical research on supply chain management: a critical review and recommendations

Despite the growing interest in supply chain management (SCM), our understanding of the subject issue is still limited, largely due to inadequate attention being placed to theory building. To address this problem, this paper highlights some major weaknesses of the extant literature with respect to the conceptualization, operationalization, and modelling of SCM, identifies potential causes underlying these shortcomings, and gives some recommendations to improve theory development in this area. Specifically, it demonstrates that (1) the SCM construct has been perceived narrowly from the perspective of a particular traditional function of a firm; (2) the construct validity is threatened due to inadequate pre-operational explication of the content domain, among other operationalization problems; and (3) the dominant conceptual SCM models focus mainly on the practices-performance relationship, overlooking the context-practices relationship. A greater advance in theory development is possible if researchers adopt a process-based view of SCM, develop conceptual SCM models based on a context-practices-performance framework, and synthesize theories and research of SCM and those of related fields such as organization studies.

A Neuro-Fuzzy Inference System Through Integration of Fuzzy Logic and Extreme Learning Machines

This paper investigates the feasibility of applying a relatively novel neural network technique, i.e., extreme learning machine (ELM), to realize a neuro-fuzzy Takagi-Sugeno-Kang (TSK) fuzzy inference system. The proposed method is an improved version of the regular neuro-fuzzy TSK fuzzy inference system. For the proposed method, first, the data that are processed are grouped by the k-means clustering method. The membership of arbitrary input for each fuzzy rule is then derived through an ELM, followed by a normalization method. At the same time, the consequent part of the fuzzy rules is obtained by multiple ELMs. At last, the approximate prediction value is determined by a weight computation scheme. For the ELM-based TSK fuzzy inference system, two extensions are also proposed to improve its accuracy. The proposed methods can avoid the curse of dimensionality that is encountered in backpropagation and hybrid adaptive neuro-fuzzy inference system (ANFIS) methods. Moreover, the proposed methods have a competitive performance in training time and accuracy compared to three ANFIS methods.

A hybrid SARIMA wavelet transform method for sales forecasting

Time series forecasting, as an important tool in many decision support systems, has been extensively studied and applied for sales forecasting over the past few decades. There are many well-established and widely-adopted forecasting methods such as linear extrapolation and SARIMA. However, their performance is far from perfect and it is especially true when the sales pattern is highly volatile. In this paper, we propose a hybrid forecasting scheme which combines the classic SARIMA method and wavelet transform (SW). We compare the performance of SW with (i) pure SARIMA, (ii) a forecasting scheme based on linear extrapolation with seasonal adjustment (CSD+LESA), and (iii) evolutionary neural networks (ENN). We illustrate the significance of SW and establish the conditions that SW outperforms pure SARIMA and CSD+LESA. We further study the time series features which influence the forecasting accuracy, and we propose a method for conducting sales forecasting based on the features of the given sales time series. Experiments are conducted by using real sales data, hypothetical data, and publicly available data sets. We believe that the proposed hybrid method is highly applicable for forecasting sales in the industry.

Electronic commerce and supply chain management: value‐adding service for clothing manufacturers

This paper presents a business‐to‐business electronic commerce (B2B EC) model for enabling supply chain management (SCM). The application of this model is substantiated by a case study of a leading clothing manufacturer in Hong Kong. On the technical side, the findings support the notion of harnessing information technologies (the Web, e‐mail, and electronic data interchange) to integrate business processes across the clothing supply chain. That is, information technologies could facilitate SCM, adding more value to customers. On the managerial side, the study highlights that manufacturers can assume a proactive role in leading changes in a supply chain, and that a fair share of gains from co‐operation must exist if collaboration between supply chain members is to be developed. Additionally, it is important for the members to have a thorough understanding of the impact of EC on inter‐firm relation‐ ship as well as the role they play in a supply chain before they engage in the virtual business world.

The process and consequences of supply chain virtualization

The recent rapid commercialization and adoption of Internet technologies has driven a process of supply chain virtualization, transforming conventional work practices across organizations. In an effort to provide a better understanding of this emerging phenomenon, this paper presents three key elements of supply chain virtualization, including: the formation of virtual trading communities; the emergence of virtual knowledge communities; and the relocation and integration of inter‐organizational business processes in the cyberspace. The transformations and consequences of virtualization are illustrated in the context of the Hong Kong textile and clothing industry. The experience of Hong Kong suggests that supply chain virtualization has propelled a structural change in buyers‐intermediaries‐sellers relationships, called for a novel approach to knowledge management, and accelerated internationalization of small‐ and medium‐sized enterprises. Managers and policy makers are advised to adopt new mindsets and practices in the face of these challenges.

Relationships between consumer decision-making styles and lifestyle characteristics: Young fashion consumers in China

Abstract This study explores the effects of lifestyle characteristics on consumer decision-making styles of young fashion consumers in China. Consumer Style Inventory (CSI), developed by Sproles and Kendall (1986) for examining different consumer decision-making styles, was adapted in this study. A questionnaire survey was employed as a tool to collect primary data and the research instrument was administered to university students in Beijing, Shanghai, Guangzhou, Hong Kong and Taipei. The results identified seven consumer decision-making styles, including recreational and hedonistic consciousness, perfectionism consciousness, habitual and brand loyal, confused by overchoice, price and value consciousness, impulsive and careless, and brand and fashion consciousness. In addition, eight lifestyle characteristics were also identified in terms of activities, interests and opinions dimensions, including “working activities”, “shopping activities”, “interests related to home”, “interests related to family”, “interests related to fashion”, “fashion as self representation”, “opinion about themselves” and “opinion about products”. Except “interests related to home”, “interests related to family” and “opinion about themselves”, all lifestyle characteristics were found to be positively and/or negatively associated with some of the consumer decision-making styles for the young consumers in China.

Developing synergistic and complementary effects in textiles and clothing (T&C) supply for Greater China

The textiles and clothing (T&C) industries in the Greater China region (China, Hong Kong, Macau and Taiwan) began to integrate with each other based on their advantageous factor endowments in line with the structural transition of economic developments since the 1980s. This rationalization has not only resulted in the T&C industry of the territory being able to secure competitive advantage in order to gain market share, but also to maintain survival under the rapid changing and competitive global marketplace. The process of integration has further accelerated and deepened after the 1990s with significant changes in the industry structure, production output, trade performance and investments taking place. There are significant opportunities for further strengthening the competitiveness in the T&C industry at both regional and international levels for the Greater China region involving the development of synergistic and complementary effects. These effects will be specially important in the product categories and other related activities across the textile production pipeline in the region. These changes are considered necessary as a response to the challenges and opportunities arising from increasingly liberalized T&C trade and increasing competition in the global market.

The impact of e-procurement on the supply chain structure

The recent advancement and deployment of information and communication technologies have created significant changes to not only the way individual businesses operate, but also the way they relate to each other. To provide a better understanding of how the internal structure and coordination mechanisms of supply chains transform through widespread e-procurement (i.e. procurement of industrial goods through exchanges in electronic markets), this paper applies a resource-based approach to examine the thesis that predicts a complete disintegration of supply chains and the dominance of electronic markets. The analysis indicates that the co-existence of electronic markets and electronic hierarchies appears to better reflect the structural transformation of supply chains, and that a strategic fit is achieved when electronic markets and electronic hierarchies are deployed for accessing commodity resources and strategic resources, respectively.

A Web-Based System for Fashion Sales Forecasting

The fashion industry faces more challenges from demand uncertainty than many other businesses because it creates products that are highly seasonal with short lifetimes and demand is inherently volatile. Such a situation introduces difficulties in fashion supply chain management. The solution to the agile supply chain involves setting up seamless or boundary-less connections between supply chain members. These connections can minimize buffers between the different stages in the chain. In an agile network, such connection is critical and can be enabled by web-software, allowing different actors to be connected without needing to have the same computer system. With integrated web systems, businesses in different geographical locations can behave as if they belong to the same enterprise. The forecasting of future sales is one of the key constituents of these solutions. Today’s enterprises in fashion often employ various IT services in supply chain operations and a forecasting system is often expected to be ac...