• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제22권1호
• /
• pp.50-55
• /
• 2016

VOC(Voice of Customer)는 기업의 제품 또는 서비스에 대한 고객의 의견이나 요구를 파악할 수 있는 중요한 데이터이다. 그러나 VOC 데이터는 대화체의 특징으로 인해 내용의 분절이나 중복이 다수 존재할 뿐 아니라 다양한 내용의 대화가 포함되어 유형을 파악하는데 어려움이 있다. 본 논문에서는, 문서에서 중요한 의미를 갖는 키워드와 품사, 형태소 등을 언어 자원으로 선정하였고, 이를 바탕으로 문장의 구조 및 의미를 이해하기 위한 LSP(Lexico-Semantic-Pattern, 어휘 의미 패턴)를 정의하여 구문 의미 이해 기반의 주요 문장을 요약문으로 추출하였다. 요약문을 생성함에 있어 분절된 문장을 연결하고 중복된 의미를 갖는 문장을 줄이는 방법을 제안하였다. 또한 카테고리 별로 어휘 의미 패턴을 정의하고 어휘 의미 패턴에 매칭된 주요 문장이 속한 카테고리를 기반으로 문서를 분류하였다. 실험에서는 VOC 데이터를 대상으로 문서를 분류하고 요약문을 생성하여 기존의 방법들과 비교하였다.

• 한국전자거래학회지
• /
• 제14권4호
• /
• pp.19-33
• /
• 2009

급속한 전자상거래의 발전으로 인하여 온라인상으로 상품을 구매하고 그에 대한 평가를 작성하는 것이 일반적인 구매 패턴이 되었다. 기존 구매자들의 상품평들은 다른 잠재적인 소비자들의 상품 구입을 이끌어내는데 큰 동기가 된다. 사용자가 작성한 상품평은 하나의 상품에 대해 실제 사용자의 좋고 나쁨에 대한 감정을 표현한 결과로, 개개인에 따라 긍정 또는 부정적인 의견으로 나눠진다. 상품평 중에서 소비자가 원하는 정보를 얻기 위해서는 이들을 일일이 수작업으로 확인해야하지만, 온라인 쇼핑몰에 상품평이 대용량으로 축적된 환경에서 이러한 작업은 비효율적일 수밖에 없다. 본 논문에서는 오피니언 마이닝 기술을 이용하여 제품 사용자의 주관적 의견을 자동으로 분류할 수 있는 감성분석 알고리즘을 제시한다. 본 논문에서 제시하는 알고리즘은 온라인 쇼핑몰에 등록된 개별 상품평을 대상으로 긍정 및 부정 의견으로 판단하여 요약된 결과를 제공하는 기능을 한다. 본 논문에서는 또한 제안된 알고리즘을 바탕으로 개발된 상품평 자동분석 시스템을 소개하고, 알고리즘의 효율성을 검증하기 위한 실험결과도 제시한다.

• 산업경영시스템학회지
• /
• 제43권4호
• /
• pp.93-106
• /
• 2020

This research explores how imported automobile companies can develop their strategies to improve the outcome of their recalls. For this, the researchers analyzed patterns of recall demand, classified recall types based on the demand patterns and examined response strategies, considering plans on how to procure parts and induce customers to visit workshops, recall execution capacity and costs. As a result, recalls are classified into four types: U-type, reverse U-type, L- type and reverse L-type. Also, as determinants of the types, the following factors are further categorized into four types and 12 sub-types of recalls: the height of maximum demand, which indicates the volatility of recall demand; the number of peaks, which are the patterns of demand variations; and the tail length of the demand curve, which indicates the speed of recalls. The classification resulted in the following: L-type, or customer-driven recall, is the most common type of recalls, taking up 25 out of the total 36 cases, followed by five U-type, four reverse L-type, and two reverse U-type cases. Prior studies show that the types of recalls are determined by factors influencing recall execution rates: severity, the number of cars to be recalled, recall execution rate, government policies, time since model launch, and recall costs, etc. As a component demand forecast model for automobile recalls, this study estimated the ARIMA model. ARIMA models were shown in three models: ARIMA (1,0,0), ARIMA (0,0,1) and ARIMA (0,0,0). These all three ARIMA models appear to be significant for all recall patterns, indicating that the ARIMA model is very valid as a predictive model for car recall patterns. Based on the classification of recall types, we drew some strategic implications for recall response according to types of recalls. The conclusion section of this research suggests the implications for several aspects: how to improve the recall outcome (execution rate), customer satisfaction, brand image, recall costs, and response to the regulatory authority.

• 경영정보학연구
• /
• 제22권4호
• /
• pp.75-92
• /
• 2020

인구 및 세대 구조가 변화면서 점차 대면 관계를 꺼리는 고객의 태도 변화가 정보기술의 발달과 스마트폰의 확산으로 더욱 커지고 있다. 이는 정보기술에 익숙해진 현대 고객들의 소비패턴인 효율성 및 신속성과도 부합되는 것으로, 오프라인 망 중심의 유통회사들이 판매 및 서비스 방식을 언택트로 전환하려는 움직임이 활발해지고 있다. 최근 다양한 분야에서 언택트 서비스가 활성화되고 있지만, 뷰티 제품의 경우 고객의 피부타입 및 상태에 따라 제품 선택이 쉽지 않으므로 비대면을 통해 제품을 추천하기가 쉽지 않다. 이와 관련하여 온라인 뷰티 분야에서 제품 추천을 위한 추천시스템 개발 및 추천 관련 연구들이 수행되었지만, 대부분이 설문조사 방법이나 소셜 데이터를 이용하여 추천 알고리즘을 개발한 연구들이었다. 즉, 고객의 피부타입이나 제품 선호도 등의 실제 사용자 정보를 기반으로 세그먼트를 분류한 연구는 부족하였다. 그리하여, 본 연구에서는 뷰티 분야에서의 언택트 서비스 중의 하나인 모바일 애플리케이션의 고객 정보와 검색 로그 데이터를 기반으로 머신러닝 기법의 K-prototypes 알고리즘을 이용하여 고객 세그먼트를 새롭게 분류하고, 이를 기반으로 언택트 마케팅 전략 방안을 제안한다. 본 연구는 머신러닝 기법을 이용하여 새롭게 고객 세그먼트를 분류함으로써 관련 기존 문헌의 범위를 확장하였다. 더불어, 언택트 서비스라는 새로운 소비 트렌드를 반영하여 고객 세그먼트를 분류하고, 이를 기반으로 뷰티 분야의 언택트 서비스에 활용할 수 있는 구체적인 방안을 제시했다는 실무적 의의가 있다.

• 한국의상디자인학회지
• /
• 제11권3호
• /
• pp.87-99
• /
• 2009

The purpose of this study was to find out criteria for classifying fashion brand from the consumer point of view. This was compared with the viewpoint of fashion business practice 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. This study was researched as the succeeding study of a model of criteria for classifying fashion brands from the viewpoint of fashion business practice. Survey was used as a research method. The subjects were 422 women who were 20-30 years old and living in and near Seoul. Questionnaires were developed based on 37 fashion brands' classification criteria by means of pre-survey, and SPSS package and LISREL program were used to analyze the data. As a result of factor analysis considering 37 classification criteria, 8 factors were identified as classification criteria. They were as follows; 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 advertising and awareness, the level of brand value, and the level of product lead ability. All of criteria were correlated to each other. The effective method to classify fashion brands was proposed by establishing the model of the relationship of the values of 7 criteria and by proving it with the structure equation model analysis. The model of criteria for classifying fashion brands that was suggested on this study was proved by the structure equation model analysis. In this study, from a consumer's point of view we suggested a theoretical framework describing which criteria would be selected to classify and utilize fashion brand market. This model can be used to select the most efficient classification criteria and classify them hierarchically instead of selecting only one among some factors that complex and interactional and classifying.

• Industrial Engineering and Management Systems
• /
• 제13권4호
• /
• pp.454-462
• /
• 2014

Retention of possible churning customer is one of the most important issues in customer relationship management, so companies try to predict churn customers using their large-scale high-dimensional data. This study focuses on dealing with large data sets by reducing the dimensionality. By using six different dimension reduction methods-Principal Component Analysis (PCA), factor analysis (FA), locally linear embedding (LLE), local tangent space alignment (LTSA), locally preserving projections (LPP), and deep auto-encoder-our experiments apply each dimension reduction method to the training data, build a classification model using the mapped data and then measure the performance using hit rate to compare the dimension reduction methods. In the result, PCA shows good performance despite its simplicity, and the deep auto-encoder gives the best overall performance. These results can be explained by the characteristics of the churn prediction data that is highly correlated and overlapped over the classes. We also proposed a simple out-of-sample extension method for the nonlinear dimension reduction methods, LLE and LTSA, utilizing the characteristic of the data.

• 대한인간공학회지
• /
• 제24권4호
• /
• pp.31-37
• /
• 2005

Resulting anthropometric data recently measured and cataloged through 5th national anthropometric survey that is called Size Korea is highly useful in clothing industries. This study aims at suggesting a statistical methodology for apparel sizing that reflects recent changes in Korean anthropometry and improves customer fitness. Based on previous research on body types such as triangular, rectangular, inverted body types, etc., factors that represent human sizes were extracted and then clustered into groups by their body types. These body type-based groups with respect to the factors obtained yielded a sizing system of which the interval of each factor is of equi-distance by their factor scores. However, each interval of the sizing system is non-linear in terms of individual anthropometric variables. The sizing system being proposed in this study was compared to that of KS K 0050 and had a broader coverage for the Korean population surveyed. The apparel sizing scheme is expected to improve customer fitness when applied to garment sizing and to provide more information on what percentage of population is included in each classification.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 추계종합학술대회
• /
• pp.495-498
• /
• 2005

본 연구에서는 전략적 마케팅을 위한 지능형 인터넷 쇼핑몰을 설계하고 구현하기 위해 고객들의 접속 기록과 상품 구매 기록 및 신상정보를 데이터마이닝 기법에 의해 통계적으로 분석하고 고객을 세분화하여, 고객이 상품에 대한 인기도에 따라 상품 진열을 자동적으로 구성할 수 있는 알고리즘 향상에 관한 연구이다. 본 시스템을 통하여 쇼핑몰 관리자의 주관적인 판단에 의해 수작업으로 이루어지는 기존의 쇼핑몰 관리 업무를 자동화 할 수 있으며, 또한 최근에 급격하게 증가하고 있는 전자상거래 시장에서 경쟁력을 강화할 수 있는 새로운 형태의 마케팅 기법을 제시할 수 있다.

• 한국IT서비스학회지
• /
• 제21권4호
• /
• pp.75-90
• /
• 2022

From the past to the present, reviews have had much influence on consumers' purchasing decisions. Companies are making various efforts, such as introducing a review incentive system to increase the number of reviews. Recently, as various types of reviews can be left, reviews have begun to be recognized as interesting new content. This way, reviews have become essential in creating loyal customers. Therefore, research and utilization of reviews are being actively conducted. Some studies analyze reviews to discover customers' needs, studies that upgrade recommendation systems using reviews, and studies that analyze consumers' emotions and attitudes through reviews. However, research that predicts the future using reviews is insufficient. This study used a dataset consisting of two reviews written in pairs with differences in usage periods. In this study, the direction of consumer product evaluation is predicted using KoBERT, which shows excellent performance in Text Deep Learning. We used 7,233 reviews collected to demonstrate the excellence of the proposed model. As a result, the proposed model using the review text and the star rating showed excellent performance compared to the baseline that follows the majority voting.

• 한국프랜차이즈경영연구
• /
• 제6권2호
• /
• pp.87-104
• /
• 2015

This study, based on theoretical and practical understanding of franchising, aims to conceptualize franchising in terms of marketing mix and proposes new paradigm of franchising. New schema of the franchise marketing mix involves both customer gap and franchisee gap by including customer and franchisee contacts and sets activities that include components of franchise system as the factor of marketing mix. So we could suggest the franchise marketing mix, '4F' by introducing conventional marketing mix concept into this assumption. The 4F schema consist of four sub-dimensions: 'Format', 'Fee & Royalty', 'Franchising Process', and 'Franchise Communication', which correspond to '4P'. In perspective of marketing mix, we could divide the franchise system into primary activity and support activity, then we also could categorize the fundamental activity into four-classification system, 4F schema. We expect that franchise marketing mix, 4F can be useful both theoretically and practically as it not only is not too different from the conventional marketing mix, but it also proposes franchise value chain by including unique characteristics and contents of the franchise system.