• Asia pacific journal of information systems
• /
• v.26 no.1
• /
• pp.66-79
• /
• 2016

The availability of detailed data on customers' online behaviors and advances in big data analysis techniques enable us to predict consumer behaviors. In the past, researchers have built purchase prediction models by analyzing clickstream data; however, these clickstream-based prediction models have had several limitations. In this study, we propose a new method for purchase prediction that combines information theory with machine learning techniques. Clickstreams from 5,000 panel members and data on their purchases of electronics, fashion, and cosmetics products were analyzed. Clickstreams were summarized using the 'entropy' concept from information theory, while 'random forests' method was applied to build prediction models. The results show that prediction accuracy of this new method ranges from 0.56 to 0.83, which is a significant improvement over values for clickstream-based prediction models presented in the past. The results indicate further that consumers' information search behaviors differ significantly across product categories.

• Fashion, Industry and Education
• /
• v.14 no.2
• /
• pp.11-23
• /
• 2016

This study investigated the comparative advantages of the Bangladeshi and Vietnamese apparel industries using Global Value Chain (GVC) framework. In this study, the GVC framework was expanded to include social and environmental sustainability issues. Secondary data, for the 2012 - 2013 period, were collected and analyzed for each component of the apparel GVC. The findings indicated that while both countries have unique comparative advantages, Vietnam clearly emerged as a leader on many GVC components. Bangladesh's comparative advantage lies in lower wages, producing high volume orders, and lean manufacturing. In spite of Vietnam's higher labor costs, it has comparative advantages in higher productivity, skilled and trained workers, manufacturing of intricate styles of high quality, agility and flexible manufacturing, more developed infrastructure and logistic services as well as greater social and environmental compliances. This study contributes towards insight into best sourcing fit for fashion brand business models. Based on the findings, fashion driven companies offering more complex styles at a faster rate will benefit from choosing Vietnam. In contrast, Bangladesh might be a better choice for high volume driven companies that offer basic apparel and better value for their consumers. From theoretical perspective, the research makes an important contribution by expanding the GVC framework.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.467-474
• /
• 2010

The market of Internet-based fashion/coordination shopping malls have been growing rapidly year by year. In accordance with this growth, Internet fashion shopping malls are also making a lot of efforts to increase their revenue by displaying new fashion products on a high spot or by having professional models wear them to make them more attractive to the customers. If online shopping malls have the functionality of automatically calculating the matching degree of lower and upper clothes, it could play a role of off-line shop assistants and provide a more convenient way of purchasing fashion products for customers. In this paper, we present a learning system adopting the content-based filtering method for online shopping malls, which automatically calculates the matching degree of lower and upper clothes and recommends the most well-matched pair.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.37 no.1
• /
• pp.76-89
• /
• 2013

The exploration of the interaction effect among the components of attractiveness is impossible; therefore, this study uses an indirect estimates approach with multiple scale items that can measure the interaction effect among the components of attractiveness to solve the problem of direct estimates. Previous studies focused on intra-store type competition as their subjects; subsequently, this study dealt with intra-store type competition as well as inter-store type competition in the competing and selecting activities among fashion retailing stores with different business models (such as department stores, road brand stores, discount stores, outlets and internet shopping malls). This study suggests a generalized model for shopping attractiveness of stores and proposes a fashion retailing store type attractiveness (FaRSTA) model instead of a simple relative importance between store selection standards.

• The Research Journal of the Costume Culture
• /
• v.28 no.6
• /
• pp.830-844
• /
• 2020

The fourth Industrial Revolution, known as digital transformation, has made MZ generation to be the focus of the new consumer market, brought about the use of technological platforms a new consumption method. Currently, as various types of content collaboration are emerging that specifically targeting at the MZ generation. Content collaboration are considered an integration of content to create new values through co-existence and co-prosperity. This study identified the characteristics of collaboration of fashion brands from 2018 using literature and online news articles, and identified and classified through case studies of it determined movie content, game and virtual characters. By this research, it shown that collaboration with movie contents have increased the collaborative synergy by using the story in global media content. Collaboration with mobile games was generally used by young casual and sportswear brands. These brands which utilized characters from mobile games popular with to attract more teen consumers and strengthen brand awareness by adding values of high-technology and scarcity to the familiar images. In addition, collaboration with virtual characters has expanded value of the collaborative approach on expanding the range of advanced digital technology, from a promotional strategy during the distribution process through to the use of virtual models. As such, collaboration using the various types of content has developed beyond simple integration of identities among various areas, integrated products or brands that as a new value.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.46 no.4
• /
• pp.638-656
• /
• 2022

This study aimed to identify characteristics of Generation MZ's consumer purchase decision journey to develop the new fashion CDJ model. The initial stage was affected by habit, online community, social media, aesthetics, circumstantial need, and proxy. In the search and consideration stage, mobile channels were used actively. In the active search and evaluation stage, online media, experiential data, and personal information were employed. In the purchase stage, zoomers took plenty of time in search and evaluation before spending, contrary to millennials who made their purchases more quickly. In the post-purchase experience stage, zoomers actively displayed follow-up behaviors depending on their satisfaction, such as retaining or deleting the app. While, millennials did not turn away from the store or brand, but followed up on their purchases even when they had an unsatisfactory experience. Based on the characteristics of CDJ, iterative cycle CDJ models were developed. Zoomers CDJ model was presented as a search loop that consists of the search and evaluation process, in which information accumulates, and a purchase loop in which the actual purchase occurs. The iterative cycle CDJ model was presented connected to the loyalty loop as the main section, which is accelerated in millennials' CDJ model.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.3
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• Journal of the Korean Society of Costume
• /
• v.59 no.6
• /
• pp.126-139
• /
• 2009

The following study from the perspective that the identity of a brand is determined by the creative work of the designer, will review the design identity of fashion house, which have maintained a basic concept of couture house until recently. For this purpose, first, the concepts of fashion house and identity could be examined, and then the design identity of both the past couture designer and the present house designer could be comparatively analyzed. This study focused on John Galliano of Dior, and was carried out under the method of document study and case study. Based on this, the analytic results of the design identity of fashion houses are as follows. The design identity of fashion house, which has its origins in the past couture house, appears from the house characteristics, design characteristics and the design image. The original design identity of Dior House seems to be feminism and elegant extravagance, which naturally models the body line of women into diverse lines. The new design identity of Dior House by Galliano, while reflecting wit and fantasy, at the same time is expressed as sexy and romantic elegance which attempts to express the beauty of modern women. The pursue of chic elegance, which is the characteristic of early Dior design, have changed into avant garde and unique designs with tendencies of multi-culturalism due to the most recent house designers. Finally, Dior house design has successfully maintained the master of handcrafted quality based on craftsmanship, the history from the house archive, and the modern trends appropriately added by the creativity of Galliano.

• Journal of Fashion Business
• /
• v.13 no.2
• /
• pp.87-99
• /
• 2009

The purpose of this study is to analyse the successful modernization strategy, and the difference between original Burberry and Burberry Prosum design. This will help in providing the fundamental information to Korean luxury fashion brands. Burberry, in particular, is rated as the most popular luxury brand in Korean fashion market. This brand has also rated 5th in sale worldwide and 1st in Korea in 2002, and was continuously been rated in 10th for the last 5 years. Related articles, fashion magazines, fashion web-site were used in this analysis, and the method was theoretical and case study. The results are divided into two categories of internal and external factors and two design patterns of check pattern and trench coat were observed. First of all, internal factor in Burberry is that they have scouted a new CEO and quickly changed their image with famous British models for the purpose of marketing strategies. They have also moved their main shop in London to Bond street, and opened shops in every country's capital cities. They were successful in achieving this by using celebrity marketing strategies with many famous celebrities. Secondly, external factor was that they have hired a designer named Christoper Bailey and this highlighted and enhanced the check pattern and trench coat. As a results, more generalized and diverse design items were presented and accessory line was enhanced, creating a much more younger image. This in turn attracted more younger customers. To sum up, original Burberry focused on classic designs, however Burberry Prosum focused on transforming traditional Burberry design into avant-garde and young. In other words, the reason for the success of this brand is highly dependent on its marketing strategies in which its uniqueness of schizophrenic cloche has appropriately represented and used in design.

• Journal of Fashion Business
• /
• v.16 no.2
• /
• pp.151-162
• /
• 2012

The industry-wide development of digital technologies has also affected the textile and fashion industries immensely. The applications of 3D technology, virtual reality, and/or augmented reality systems have helped to create novel fashion brands based on the marriage of IT and textile/fashion industries. 3D digital virtual clothing systems have been developed to help the textile and fashion industries in terms of the planning, manufacturing, marketing and sales sectors. So far, most of the development effort for the 3d virtual clothing systems has been focused on the woven fabrics. The characteristics of woven fabrics differ from those of knitted fabric. Since the physical structures and mechanical properties of the knitted fabrics are definitely different from those of woven fabrics, the simulation process for the knitted fabrics should follow different approaches. The loops in a knitted fabric deform easily. The deformation results in a readily stretchable fabric appearance. Cloth simulation mostly employs models that approximate the mechanical properties of linear elastic planes. This simulation scheme does not, however, describe well enough the behavior of knitted fabrics, which deviate largely from the linear isotropic material characteristics. This study aims at characterizing the tensile deformation and surface textures of a knitted fabric product. Tensile deformation curves for the wale, course, and bias direction are analyzed. The surface texture of the knitted fabric is analyzed by using a 3-dimensional scanning device.