• 정보처리학회논문지D
• /
• 제9D권5호
• /
• pp.945-954
• /
• 2002

인터넷을 통한 비즈니스에 수익 모델에 대한 관심이 높아지면서 방문자별로 개인화된 서비스를 제공하려는 노력이 커지고 있다. 개인화(Personalization)란 고객 한 명을 대상으로 하여 그 고객 한 사람을 위한 정보나 제품을 제공해주는 작업을 말한다. 개인화 서비스를 위해서 전 처리과정인 사용자 프로파일 생성과정이 필요하며, 적극적인 개인화 서비스를 제공하기 위해서는 충분한 고객 데이터가 필요하다. 본 논문에서는 웹사이트 상에서 사용자 행위 패턴을 파악할 수 있는 클릭스트림 정보를 모듈화 하였으며, 이를 이용하여 확장된 웹 로그 시스템을 구현하였다. 클릭스트림 정보를 웹 로그정보에 포함시켜 사용자의 행위 패턴을 파악할 수 있도록 웹 서버 시스템을 설계하고 구현하였다. 그리고 이 웹 서버는 웹사이트로부터 얻은 클릭스트림 정보를 분류하고 저장하여 관리자가 쉽게 분석할 수 있다. 이때 데이터베이스 저장 기술로 OLE DB Provider상에서 수행되는 ADO(ActiveX Data Object)기술을 사용함으로써 확장된 웹 로그 처리 시스템을 설계하였다. 확장된 웹 로그 DB를 패턴분석, 군집분석 등의 마이닝(Mining) 기법을 통하여 맞춤서비스에 대한 사용자 프로파일을 구축할 수 있다.

• 한국경영과학회지
• /
• 제33권3호
• /
• pp.59-76
• /
• 2008

Studies of recommender systems have focused on improving their performance in terms of error rates between the actual and predicted preference values. Also, many studies have been conducted to investigate the relationships between customer information processing and the characteristics of recommender systems via surveys and web-based experiments. However, the actual impact of recommendation on product pages for customer browsing behavior and decision-making in the commercial environment has not, to the best of our knowledge, been investigated with actual clickstream data. The principal objective of this research is to assess the effects of product recommendation on customer behavior in e-Commerce, using actual clickstream data. For this purpose, we utilized an online bookstore's clickstream data prior to and after the web site renovation of the store. We compared the recommendation effects on customer behavior with the data. From these comparisons, we determined that the relevant recommendations in product pages have positive relationships with the acquisition of customer attention and elaboration. Additionally, the placing of recommended items in shopping cart is positively related to suggesting the relevant recommendations. However, the frequencies at which the recommended items were purchased did not differ prior to and after the renovation of the site.

• Journal of Smart Tourism
• /
• 제2권2호
• /
• pp.15-19
• /
• 2022

Destination marketing organizations (DMOs) utilize the official website for marketing and promotional purposes, while tourists often navigate through the official website to gather necessary information for their upcoming trips. With the advancement of business analytics, DMOs may need to exploit the clickstream data generated through their official website to develop more suitable and persuasive strategic marketing and promotional activities. As such, the primary objective of the current study is to show whether clickstream data can successfully identify the trip purposes of a particular user. Using a latent class analysis and multinomial logistic regression, this study found the meaningful and statistically significant variations in webpage visits among different trip purpose groups (e.g., weekend getaways, day-trippers, and other purposes). The findings of this study would provide a foundation for more data-centric destination marketing and management practice.

• 한국경영정보학회:학술대회논문집
• /
• 한국경영정보학회 2008년도 춘계학술대회
• /
• pp.135-140
• /
• 2008

Studies of recommender systems have focused on improving their performance in terms of error rates between the actual and predicted preference values. Also, many studies have been conducted to investigate the relationships between customer information processing and the characteristics of recommender systems via surveys and web-based experiments. However, the actual impact of recommendation on product pages for customer browsing behavior and decision-making in the commercial environment has not, to the best of our knowledge, been investigated with actual clickstream data. The principal objective of this research is to assess the effects of product recommendation on customer behavior in e-Commerce, using actual clickstream data. For this purpose, we utilized an online bookstore's clickstream data prior to and after the web site renovation of the store. We compared the recommendation effects on customer behavior with the data. From these comparisons, we determined that the relevant recommendations in product pages have positive relationships with the acquisition of customer attention and elaboration. Additionally, the placing of recommended items in shopping cart is positively related to suggesting the relevant recommendations. However, the frequencies at which the recommended items were purchased did not differ prior to and after the renovation of the site.

• Asia pacific journal of information systems
• /
• 제26권1호
• /
• 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.

• 지능정보연구
• /
• 제22권3호
• /
• pp.143-163
• /
• 2016

인구통계학적 정보는 디지털 마케팅의 핵심이라 할 수 있는 인터넷 사용자에 대한 타겟 마케팅 및 개인화된 광고를 위해 고려되는 가장 기초적이고 중요한 정보이다. 하지만 인터넷 사용자의 온라인 활동은 익명으로 행해지는 경우가 많기 때문에 인구통계특성 정보를 수집하는 것은 쉬운 일이 아니다. 정기적인 설문 조사를 통해 사용자들의 인구통계특성 정보를 수집할 수도 있지만 많은 비용이 들며 허위 기재 등과 같은 위험성이 존재한다. 특히, 모바일 환경에서는 대부분의 사용자들이 익명으로 활동하기 때문에 인구통계특성 정보를 수집하는 것은 더욱 더 어려워지고 있다. 반면, 인터넷 사용자의 온라인 활동을 기록한 클릭스트림 데이터는 해당 사용자의 인구통계학적 정보에 활용될 수 있다. 특히, 인터넷 사용자의 온라인 행위 특성 중 하나인 페이지뷰는 인구통계학적 정보 예측에 있어서 중요한 요인이 된다. 본 연구에서는 기존 선행 연구를 토대로 클릭스트림 데이터 분석을 통해 인터넷 사용자의 온라인 행위 특성을 추출하고 이를 해당 사용자의 인구통계학적 정보 예측에 사용한다. 또한, 1)의사결정나무를 이용한 변수 축소, 2)주성분분석을 활용한 차원축소, 3)군집분석을 활용한 변수축소의 방법을 제안하고 실험에 적용함으로써 많은 설명변수를 이용하여 예측 모델 생성 시 발생하는 차원의 저주와 과적합 문제를 해결하고 예측 모델의 정확도를 높이고자 하였다. 실험 결과, 범주의 수가 많은 다분형 종속변수에 대한 예측 모델은 모든 설명변수를 사용하여 예측 모델을 생성했을 때보다 본 연구에서 제안한 방법론들을 적용했을 때 예측 모델에 대한 정확도가 향상됨을 알 수 있었다. 본 연구는 클릭스트림 분석을 통해 추출된 인터넷 사용자의 온라인 행위는 해당 사용자의 인구통계학적 정보 예측에 활용 가능하며, 예측된 익명의 인터넷 사용자들에 대한 인구통계학적 정보를 디지털 마케팅에 활용 할 수 있다는데 의의가 있다. 또한, 제안 방법론들을 통해 어느 종속변수에 대해 어떤 방법론들이 예측 모델의 정확도를 개선하는지 확인하였다. 이는 추후 클릭스트림 분석을 활용하여 인구통계학적 정보를 예측할 때, 본 연구에서 제안한 방법론을 사용하여 보다 높은 정확도를 가지는 예측 모델을 생성 할 수 있다는데 의의가 있다.

• Asia pacific journal of information systems
• /
• 제31권4호
• /
• pp.606-632
• /
• 2021

With many consumers being exposed to news via social media platforms, news organizations are challenged to attract visitors and generate revenue during visits to their websites. They therefore need detailed information on how to write articles and headlines to increase visitors' engagement with the content to drive advertising revenues. For those news organizations whose business model depends mainly on advertisements, rather than subscriptions, it is particularly crucial to understand what makes the website attractive to their visitors, what drives users to stay on the website, and what factors affect a user's exit decision. The current research examines individual news consumers' choices to find patterns of increase or decrease in user engagement relative to a variety of topics, as well as to the mood or tone of the content. Using clickstream data from a major news organization, the authors develop a user-level dynamic model of clickstream behavior that takes into account the content of both headlines and stories that visitors read. The authors find that readers appear to exhibit state dependence in the tone of the articles that they read. They also show how the topics expressed in headlines can affect the amount of content readers consume when visiting the news organization to a much larger degree than the topics expressed in the content of the article. Online publishers can make use of such findings to present visitors with content that is likely to maintain and/or increase their engagement and consequently drive advertising revenue.

• 한국IT서비스학회지
• /
• 제7권2호
• /
• pp.59-75
• /
• 2008

Despite our extensive understanding on the Internet business and widely understood first-mover advantage. it is not clearly answered yet whether an internet firm can enjoy the first-mover advantage in the new environment of the Internet. This is mainly because the Internet marketplace itself has a complex combination of various business models, ranging from a simple channel-extension to a whole new business model. Based on new theoretical development on the first-mover advantage, we empirically test whether being an early mover in the Internet environment materially affects firm performance, using clickstream data from Korea where broadband Internet installation is ranked as top among OECD countries. Our results show the effectiveness of first-mover advantage on the web does not exist, regardless of its business model and competitive environment. This result expands our understandings on the e-business, not to mention of the real feature of first-mover advantage.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.737-767
• /
• 2023

With the availability of big customer data and advances in machine learning techniques, the prediction of customer behavior at the session-level has attracted considerable attention from marketing practitioners and scholars. This study aims to predict customer purchase conversion at the session-level by employing customer profile, transaction, and clickstream data. For this purpose, we develop a multimodal deep learning fusion model with dynamic and static features (i.e., DS-fusion). Specifically, we base page views within focal visist and recency, frequency, monetary value, and clumpiness (RFMC) for dynamic and static features, respectively, to comprehensively capture customer characteristics for buying behaviors. Our model with deep learning architectures combines these features for conversion prediction. We validate the proposed model using real-world e-commerce data. The experimental results reveal that our model outperforms unimodal classifiers with each feature and the classical machine learning models with dynamic and static features, including random forest and logistic regression. In this regard, this study sheds light on the promise of the machine learning approach with the complementary method for different modalities in predicting customer behaviors.

• 한국경영정보학회:학술대회논문집
• /
• 한국경영정보학회 2007년도 International Conference
• /
• pp.382-387
• /
• 2007

Since the emergence of Internet service, the revenue from e-commerce has been exponentially growing. Especially, the consumption by men in online retailers is distinctively different from that in traditional bricks-and-mortar retailers. Facing these interesting phenomena, researchers as well as businesses have begun to pay attention to e-commerce and online consumers. However, research on consumer behaviors in the online channel has not made a careful investigation into gender behavioral differences in the online channel. Therefore, we provide a profound understanding of gender differences in online shopping behavior compared to those in offline shopping behaviors. Through our findings from this research, we draw researchers' attention to consumer behavior in the online channel, gender differences in online shopping. Also, we suggest practical implications to online marketers using data collected from one of the major online retailers.