• Asia pacific journal of information systems
• /
• v.20 no.2
• /
• pp.23-37
• /
• 2010

Conventional Support Vector Machines (SVMs) have been utilized as classifiers for binary classification problems. However, certain real world problems, including corporate bond rating, cannot be addressed by binary classifiers because these are multi-class problems. For this reason, numerous studies have attempted to transform the original SVM into a multiclass classifier. These studies, however, have only considered nominal classification problems. Thus, these approaches have been limited by the existence of multiclass classification problems where classes are not nominal but ordinal in real world, such as corporate bond rating and multiclass customer classification. In this study, we adopt a novel multiclass SVM which can address ordinal classification problems using ordinal pairwise partitioning (OPP). The proposed model in our study may use fewer classifiers, but it classifies more accurately because it considers the characteristics of the order of the classes. Although it can be applied to all kinds of ordinal multiclass classification problems, most prior studies have applied it to finance area like bond rating. Thus, this study applies it to a real world customer level classification case for implementing customer relationship management. The result shows that the ordinal multiclass SVM model may also be effective for customer level classification.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.4 no.3
• /
• pp.33-42
• /
• 2002

The purpose of this study was to find out criteria for classifying fashion brand from consumer point of view in order to develop strategy of fashion brands and to manage brand effectively and systematically, and to suggest theoretical frame for application of these criteria. Survey was used as a research method. Subject were 422 age of 20-30 women living in and near Seoul. Questionnaires was developed to based on 37 classification criteria, and SPSS package program were used to analyze data. The results of this study were as follows: First, factor analysis considering 37 classification criteria identified 8 factors as classification criteria. They were the level of brand form, the level of product concept, the level of management item, the level of brand sales ability, the level of customer management, the level of brand advertizing and awareness, the level of brand value, the level of product lead ability. Second, the most important factor was the level of customer management, but comparatively factor of the level of brand sales ability the level of brand value was less important. Third, consumer cognized difference of criteria for classifying fashion brands. And the level of product lead ability was the most important factor in women's wear category and the level of brand form was in general casual wear category.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.206-213
• /
• 2003

Application of existing decision tree algorithms for Internet retail customer classification is apt to construct a bushy tree due to imprecise source data. Even excessive analysis may not guarantee the effectiveness of the business although the results are derived from fully detailed segments. Thus, it is necessary to determine the appropriate number of segments with a certain level of abstraction. In this study, we developed a stopping rule that considers the total amount of information gained while generating a rule tree. In addition to forwarding from root to intermediate nodes with a certain level of abstraction, the decision tree is investigated by the backtracking pruning method with misclassification loss information.

• Journal of Information Technology Applications and Management
• /
• v.10 no.4
• /
• pp.51-63
• /
• 2003

This study designs and implements a new approach to the classification of e-mail requests from customer based on machine learning techniques. The work on building an electronic mall classifier can be cast into the framework of text classification, since an e-mail is a viewed as a document, and judgement of interest is viewed as a class level given to the e-mail document. It is also implemented an e-mall based automated response system that integrate with Call Center in a practical use.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.107-123
• /
• 2021

In an online shopping site or offline store, products purchased by each customer over time form the purchase history of the customer. Also, in most retailers, products have a product taxonomy, which represents a hierarchical classification of products. Considering the product taxonomy, the lower the level of the category to which two products both belong, the more similar the two products. However, there has been little work on similarity measures for sequences considering a hierarchical classification of elements. In this paper, we propose new similarity measures for purchase histories considering not only the purchase order of products but also the hierarchical classification of products. Unlike the existing methods, where the similarity between two elements in sequences is only 0 or 1 depending on whether two elements are the same or not, the proposed method can assign any real number between 0 and 1 considering the hierarchical classification of elements. We apply this idea to extend three existing representative similarity measures for sequences. We also propose an efficient computation method for the proposed similarity measures. Through various experiments, we show that the proposed method can measure the similarity between purchase histories very effectively and efficiently.

• Journal of the Korea Safety Management & Science
• /
• v.20 no.1
• /
• pp.41-55
• /
• 2018

For several decades, attribute classification methods using the asymmetrical relationship between an attribute performance and the satisfaction of that attribute have been explored by numerous researchers. In particular, the Kano model, which classifies quality attributes into 5 elements using simple questionnaire and two-dimensional evaluation table, has gained popularity: Attractive, One-dimensional, Must-be, Indifferent, and Reverse quality. As Kano's model is well accepted, many literatures have introduced categorization methods using the Kano's evaluation table at attribute level. However, they applied different terminologies and classification criteria and this causes confusion and misunderstanding. Therefore, a criterion for quality classification at attribute level is necessary. This study is aimed to suggest a new attribute classification method that sub-categorizes quality attributes using 5-point ordinal point and Kano's two-dimensional evaluation table through an extensive literature review. For this, the current study examines the intrinsic and extrinsic problems of the well-recognized Kano model that have been used for measuring customer satisfaction of products and services. For empirical study, the author conducted a comparative study between the results of Kano's model and the proposed method for an e-learning case (33 attributes). Results show that the proposed method is better in terms of ease of use and understanding of kano's results and this result will contribute to the further development of the attractive quality theory that enables to understand both the customers explicit and implicit needs.

• Journal of Information Technology Services
• /
• v.15 no.1
• /
• pp.197-210
• /
• 2016

With the advent of text analytics, VOC (Voice of Customer) data become an important resource which provides the managers and marketing practitioners with consumer's veiled opinion and requirements. In other words, making relevant use of VOC data potentially improves the customer responsiveness and satisfaction, each of which eventually improves business performance. However, unstructured data set such as customers' complaints in VOC data have seldom used in marketing practices such as predicting service time as an index of service quality. Because the VOC data which contains unstructured data is too complicated form. Also that needs convert unstructured data from structure data which difficult process. Hence, this study aims to propose a prediction model to improve the estimation accuracy of the level of customer satisfaction by combining unstructured from textmining with structured data features in VOC. Also the relationship between the unstructured, structured data and service processing time through the regression analysis. Text mining techniques, sentiment analysis, keyword extraction, classification algorithms, decision tree and multiple regression are considered and compared. For the experiment, we used actual VOC data in a company.

• Journal of Korean Society for Quality Management
• /
• v.33 no.3
• /
• pp.71-90
• /
• 2005

New high-speed rail service, the Korea Train Express(KTX), has been beginning service in Korea. We measured the service quality of the Korea Train Express and comparatively analyzed the service quality of domestic flight and express buses which are means of long distance transportation. Furthermore, by using the Kano model, the perception level of the service of customers is not only segmented in groups but also switching barriers are derived. As a result, the customers by group have a difference in the level of their perception. While in both high-speed bullet train service and flights dimensions significantly affect the customer satisfaction and retention excluding a responsiveness dimension, in the Train Express four dimensions(Reliability, Responsiveness, Assurance, Tangibles) with the exception of Empathy which significantly affect the customer satisfaction and retention.

• Asia Marketing Journal
• /
• v.10 no.2
• /
• pp.125-151
• /
• 2008

Both companies and consumers are highly interested in on-line customer reviews which enable consumers to share their experience and knowledge about products. In this study, after classifying real reviews into context units and deriving categories, we analyzed differences between categories based on channel(manufacturers' homepage/ shopping mall), product attribute(search/experience) and price(high/low). The method to derive categories is based on roughly adopting constructs of ACSI model and elaborate and repetitive classification of real reviews. We set up the classification category with 3 levels. Level 1 consists of product and service, level 2 consists of function, design, price, purchase motive, suggestion/user-tip and recommendation/repurchase in product and AS/up-grade and delivery/others in service and level 3 is composed of details of level 2 of category. We could find remarkable differences between channels in all 8 items of level 2 of category. As the number of context units in homepage is more than in shopping mall, we found reviews in homepage is more concrete. Moreover, overall satisfaction in review was higher at homepage's. Also, in product attribute dimension, we found different patterns of reviews in design, purchase motive, suggestion/user-tip, recommendation/repurchase, AS/up-grade and delivery/others and no difference in overall customer's satisfaction. In price dimension, we found differences between high and low price in design, price and AS/up-grade and no difference in overall customer's satisfaction.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.05a
• /
• pp.305-314
• /
• 2002

In order to adapt to today's rapidly changing environment and gain a competitive advantage, many companies are interested in CRM(Customer Relationship Management). Especially, the product recommendation system that can be implemented by personalizing the marketing strategy becomes the focus of CRM. In this research, we employed CBR(Case-Based Reasoning) technique that can overcome the limitation of CF(Collaborative Filtering) technique. Our system recommends the books that the customer is very likely to buy next time considering the factors such as 'Personal Features of Customer,' Similarity between Book Categories' and 'Sequence of Book Purchases'. Accuracy of predicting a book-not a particular book, but in the middle level of classification that contains about 190 categories-was about 57%.